Hugging Face's logo

htlou
/
mm-interp-RLAIF-V-Dataset-llava-mistral

Image-Text-to-Text
Transformers
Safetensors
llava_next
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
htlou commited on
Commit
5acd714
·
verified ·
1 Parent(s): d3210a1

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +94 -0
  2. added_tokens.json +4 -0
  3. all_results.json +20 -0
  4. checkpoint-120/added_tokens.json +4 -0
  5. checkpoint-120/config.json +68 -0
  6. checkpoint-120/generation_config.json +6 -0
  7. checkpoint-120/model-00001-of-00004.safetensors +3 -0
  8. checkpoint-120/model-00002-of-00004.safetensors +3 -0
  9. checkpoint-120/model-00003-of-00004.safetensors +3 -0
  10. checkpoint-120/model-00004-of-00004.safetensors +3 -0
  11. checkpoint-120/model.safetensors.index.json +694 -0
  12. checkpoint-120/preprocessor_config.json +52 -0
  13. checkpoint-120/special_tokens_map.json +30 -0
  14. checkpoint-120/tokenizer.json +0 -0
  15. checkpoint-120/tokenizer.model +3 -0
  16. checkpoint-120/tokenizer_config.json +70 -0
  17. checkpoint-120/trainer_state.json +441 -0
  18. checkpoint-120/training_args.bin +3 -0
  19. checkpoint-160/added_tokens.json +4 -0
  20. checkpoint-160/config.json +68 -0
  21. checkpoint-160/generation_config.json +6 -0
  22. checkpoint-160/model-00001-of-00004.safetensors +3 -0
  23. checkpoint-160/model-00002-of-00004.safetensors +3 -0
  24. checkpoint-160/model-00003-of-00004.safetensors +3 -0
  25. checkpoint-160/model-00004-of-00004.safetensors +3 -0
  26. checkpoint-160/model.safetensors.index.json +694 -0
  27. checkpoint-160/preprocessor_config.json +52 -0
  28. checkpoint-160/special_tokens_map.json +30 -0
  29. checkpoint-160/tokenizer.json +0 -0
  30. checkpoint-160/tokenizer.model +3 -0
  31. checkpoint-160/tokenizer_config.json +70 -0
  32. checkpoint-160/trainer_state.json +577 -0
  33. checkpoint-160/training_args.bin +3 -0
  34. checkpoint-200/added_tokens.json +4 -0
  35. checkpoint-200/config.json +68 -0
  36. checkpoint-200/generation_config.json +6 -0
  37. checkpoint-200/model-00001-of-00004.safetensors +3 -0
  38. checkpoint-200/model-00002-of-00004.safetensors +3 -0
  39. checkpoint-200/model-00003-of-00004.safetensors +3 -0
  40. checkpoint-200/model-00004-of-00004.safetensors +3 -0
  41. checkpoint-200/model.safetensors.index.json +694 -0
  42. checkpoint-200/preprocessor_config.json +52 -0
  43. checkpoint-200/special_tokens_map.json +30 -0
  44. checkpoint-200/tokenizer.json +0 -0
  45. checkpoint-200/tokenizer.model +3 -0
  46. checkpoint-200/tokenizer_config.json +70 -0
  47. checkpoint-200/trainer_state.json +713 -0
  48. checkpoint-200/training_args.bin +3 -0
  49. checkpoint-240/added_tokens.json +4 -0
  50. checkpoint-240/config.json +68 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: llava-hf/llava-v1.6-mistral-7b-hf
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: RLAIF-V-Dataset
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # RLAIF-V-Dataset
18
+
19
+ This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the RLAIF-V-Dataset dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4513
22
+ - Rewards/chosen: -3.2808
23
+ - Rewards/rejected: -6.0928
24
+ - Rewards/accuracies: 0.8212
25
+ - Rewards/margins: 2.8121
26
+ - Logps/rejected: -219.8085
27
+ - Logps/chosen: -191.2850
28
+ - Logits/rejected: -2.2605
29
+ - Logits/chosen: -2.2964
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 1e-06
49
+ - train_batch_size: 8
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - distributed_type: multi-GPU
53
+ - num_devices: 8
54
+ - gradient_accumulation_steps: 4
55
+ - total_train_batch_size: 256
56
+ - total_eval_batch_size: 64
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: cosine
59
+ - lr_scheduler_warmup_steps: 10
60
+ - num_epochs: 3.0
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.5989 | 0.1368 | 40 | 0.6069 | -0.3887 | -0.8615 | 0.6365 | 0.4728 | -167.4954 | -162.3644 | -2.4012 | -2.4102 |
67
+ | 0.5452 | 0.2735 | 80 | 0.5331 | -0.8812 | -1.8338 | 0.7135 | 0.9526 | -177.2182 | -167.2896 | -2.5177 | -2.5334 |
68
+ | 0.5026 | 0.4103 | 120 | 0.4925 | -1.4411 | -2.6703 | 0.7442 | 1.2292 | -185.5836 | -172.8887 | -1.9765 | -2.0268 |
69
+ | 0.4511 | 0.5470 | 160 | 0.4683 | -1.3283 | -3.0284 | 0.7625 | 1.7001 | -189.1644 | -171.7603 | -2.0280 | -2.0709 |
70
+ | 0.4562 | 0.6838 | 200 | 0.4528 | -1.4943 | -3.2675 | 0.7567 | 1.7732 | -191.5553 | -173.4200 | -2.1029 | -2.1462 |
71
+ | 0.4189 | 0.8205 | 240 | 0.4494 | -1.9309 | -3.8899 | 0.7663 | 1.9589 | -197.7792 | -177.7867 | -2.4165 | -2.4472 |
72
+ | 0.4484 | 0.9573 | 280 | 0.4432 | -1.7397 | -3.8238 | 0.7635 | 2.0841 | -197.1187 | -175.8746 | -2.1586 | -2.2000 |
73
+ | 0.222 | 1.0940 | 320 | 0.4504 | -1.2207 | -2.9698 | 0.7760 | 1.7491 | -188.5780 | -170.6839 | -2.4060 | -2.4397 |
74
+ | 0.2018 | 1.2308 | 360 | 0.4438 | -2.0855 | -4.4746 | 0.7885 | 2.3891 | -203.6262 | -179.3325 | -2.3445 | -2.3790 |
75
+ | 0.2017 | 1.3675 | 400 | 0.4350 | -1.9109 | -4.1414 | 0.7981 | 2.2305 | -200.2943 | -177.5862 | -2.3022 | -2.3351 |
76
+ | 0.1999 | 1.5043 | 440 | 0.4288 | -2.1056 | -4.4641 | 0.8048 | 2.3585 | -203.5214 | -179.5331 | -2.1361 | -2.1716 |
77
+ | 0.1837 | 1.6410 | 480 | 0.4262 | -2.2318 | -4.7056 | 0.8125 | 2.4738 | -205.9359 | -180.7949 | -2.2127 | -2.2452 |
78
+ | 0.1942 | 1.7778 | 520 | 0.4163 | -2.3806 | -5.0283 | 0.8115 | 2.6478 | -209.1637 | -182.2829 | -2.3333 | -2.3675 |
79
+ | 0.1821 | 1.9145 | 560 | 0.4165 | -2.2038 | -4.6709 | 0.8173 | 2.4671 | -205.5893 | -180.5155 | -2.3238 | -2.3543 |
80
+ | 0.0858 | 2.0513 | 600 | 0.4415 | -2.7029 | -5.1979 | 0.8144 | 2.4950 | -210.8597 | -185.5066 | -2.2872 | -2.3220 |
81
+ | 0.0832 | 2.1880 | 640 | 0.4414 | -2.8951 | -5.6554 | 0.8173 | 2.7603 | -215.4344 | -187.4282 | -2.2892 | -2.3247 |
82
+ | 0.0817 | 2.3248 | 680 | 0.4521 | -3.2403 | -6.0014 | 0.8154 | 2.7611 | -218.8945 | -190.8804 | -2.2697 | -2.3056 |
83
+ | 0.0858 | 2.4615 | 720 | 0.4479 | -3.3847 | -6.3012 | 0.8221 | 2.9165 | -221.8926 | -192.3248 | -2.2708 | -2.3072 |
84
+ | 0.0723 | 2.5983 | 760 | 0.4574 | -3.3436 | -6.1113 | 0.8173 | 2.7677 | -219.9932 | -191.9133 | -2.2754 | -2.3103 |
85
+ | 0.0717 | 2.7350 | 800 | 0.4532 | -3.3171 | -6.1289 | 0.8192 | 2.8118 | -220.1688 | -191.6483 | -2.2610 | -2.2973 |
86
+ | 0.0691 | 2.8718 | 840 | 0.4514 | -3.2739 | -6.0855 | 0.8212 | 2.8116 | -219.7354 | -191.2166 | -2.2604 | -2.2964 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.45.2
92
+ - Pytorch 2.4.0+cu121
93
+ - Datasets 2.21.0
94
+ - Tokenizers 0.20.3
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
all_results.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.994871794871795,
3
+ "eval_logits/chosen": -2.296416759490967,
4
+ "eval_logits/rejected": -2.2604804039001465,
5
+ "eval_logps/chosen": -191.28500366210938,
6
+ "eval_logps/rejected": -219.8085479736328,
7
+ "eval_loss": 0.4512675702571869,
8
+ "eval_rewards/accuracies": 0.8211538195610046,
9
+ "eval_rewards/chosen": -3.2807652950286865,
10
+ "eval_rewards/margins": 2.812060594558716,
11
+ "eval_rewards/rejected": -6.092825889587402,
12
+ "eval_runtime": 509.575,
13
+ "eval_samples_per_second": 16.316,
14
+ "eval_steps_per_second": 0.255,
15
+ "total_flos": 1.0330118169821184e+16,
16
+ "train_loss": 0.2632859356310134,
17
+ "train_runtime": 40450.3897,
18
+ "train_samples_per_second": 5.549,
19
+ "train_steps_per_second": 0.022
20
+ }
checkpoint-120/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
checkpoint-120/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 4096,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 336,
11
+ 672
12
+ ],
13
+ [
14
+ 672,
15
+ 336
16
+ ],
17
+ [
18
+ 672,
19
+ 672
20
+ ],
21
+ [
22
+ 1008,
23
+ 336
24
+ ],
25
+ [
26
+ 336,
27
+ 1008
28
+ ]
29
+ ],
30
+ "image_seq_length": 576,
31
+ "image_token_index": 32000,
32
+ "model_type": "llava_next",
33
+ "projector_hidden_act": "gelu",
34
+ "text_config": {
35
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
36
+ "architectures": [
37
+ "MistralForCausalLM"
38
+ ],
39
+ "intermediate_size": 14336,
40
+ "max_position_embeddings": 32768,
41
+ "model_type": "mistral",
42
+ "num_key_value_heads": 8,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 1000000.0,
45
+ "sliding_window": null,
46
+ "torch_dtype": "bfloat16",
47
+ "vocab_size": 32064
48
+ },
49
+ "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.45.2",
52
+ "use_cache": false,
53
+ "use_image_newline_parameter": true,
54
+ "vision_config": {
55
+ "hidden_size": 1024,
56
+ "image_size": 336,
57
+ "intermediate_size": 4096,
58
+ "model_type": "clip_vision_model",
59
+ "num_attention_heads": 16,
60
+ "num_hidden_layers": 24,
61
+ "patch_size": 14,
62
+ "projection_dim": 768,
63
+ "vocab_size": 32000
64
+ },
65
+ "vision_feature_layer": -2,
66
+ "vision_feature_select_strategy": "default",
67
+ "vocab_size": 32064
68
+ }
checkpoint-120/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
+ }
checkpoint-120/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459e1ca7f96c1c0f8be968e62464fdd589985eaabdc3b0cfb0ed12496598241f
3
+ size 4921618624
checkpoint-120/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07dedc2fe1eefc458ebb8d7b609768650e159ddb1cab205ae290874b736078b4
3
+ size 4915917672
checkpoint-120/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11bf54abd477fab6efc72a3d07bafd09a364652d5fdd40ee6bb047e6010a0179
3
+ size 4915917680
checkpoint-120/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a13d2c37b8fa7b8f366f24a1b0bb5c03b649d063b8b4403b47b56c6d249d622
3
+ size 380134008
checkpoint-120/model.safetensors.index.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15133495296
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
298
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
299
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
300
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
301
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
302
+ "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
303
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
304
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
305
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
316
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
317
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
322
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
323
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
324
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
325
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
326
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
327
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
328
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
329
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
330
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
331
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
332
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
333
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
334
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
335
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
336
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
337
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
342
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
343
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
344
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
345
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
346
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
347
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
348
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
349
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
350
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
351
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
352
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
400
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
401
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
406
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
407
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
408
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
432
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
433
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
434
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
435
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
436
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
437
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
438
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
439
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
440
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
441
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
444
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
445
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
693
+ }
694
+ }
checkpoint-120/preprocessor_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_grid_pinpoints": [
14
+ [
15
+ 336,
16
+ 672
17
+ ],
18
+ [
19
+ 672,
20
+ 336
21
+ ],
22
+ [
23
+ 672,
24
+ 672
25
+ ],
26
+ [
27
+ 1008,
28
+ 336
29
+ ],
30
+ [
31
+ 336,
32
+ 1008
33
+ ]
34
+ ],
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_processor_type": "LlavaNextImageProcessor",
41
+ "image_std": [
42
+ 0.26862954,
43
+ 0.26130258,
44
+ 0.27577711
45
+ ],
46
+ "processor_class": "LlavaNextProcessor",
47
+ "resample": 3,
48
+ "rescale_factor": 0.00392156862745098,
49
+ "size": {
50
+ "shortest_edge": 336
51
+ }
52
+ }
checkpoint-120/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-120/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-120/tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {
53
+ "image_token": "<image>"
54
+ },
55
+ "image_token": "<image>",
56
+ "legacy": true,
57
+ "max_length": null,
58
+ "model_max_length": 1000000000000000019884624838656,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "<pad>",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "processor_class": "LlavaNextProcessor",
64
+ "sp_model_kwargs": {},
65
+ "spaces_between_special_tokens": false,
66
+ "split_special_tokens": false,
67
+ "tokenizer_class": "LlamaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.41025641025641024,
5
+ "eval_steps": 40,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017094017094017096,
13
+ "grad_norm": 35.038580788061665,
14
+ "learning_rate": 5e-07,
15
+ "logits/chosen": -2.7457876205444336,
16
+ "logits/rejected": -2.7444841861724854,
17
+ "logps/chosen": -164.26461791992188,
18
+ "logps/rejected": -170.55870056152344,
19
+ "loss": 0.6935,
20
+ "rewards/accuracies": 0.26875001192092896,
21
+ "rewards/chosen": 0.003455913159996271,
22
+ "rewards/margins": -0.0019886991940438747,
23
+ "rewards/rejected": 0.0054446132853627205,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.03418803418803419,
28
+ "grad_norm": 36.203903910498276,
29
+ "learning_rate": 1e-06,
30
+ "logits/chosen": -2.7106502056121826,
31
+ "logits/rejected": -2.716397523880005,
32
+ "logps/chosen": -171.80043029785156,
33
+ "logps/rejected": -165.20602416992188,
34
+ "loss": 0.6875,
35
+ "rewards/accuracies": 0.5062500238418579,
36
+ "rewards/chosen": 0.012000308372080326,
37
+ "rewards/margins": 0.0025437879376113415,
38
+ "rewards/rejected": 0.009456520900130272,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.05128205128205128,
43
+ "grad_norm": 33.9576577784673,
44
+ "learning_rate": 9.999177507263144e-07,
45
+ "logits/chosen": -2.651571750640869,
46
+ "logits/rejected": -2.629457473754883,
47
+ "logps/chosen": -174.04080200195312,
48
+ "logps/rejected": -174.0542755126953,
49
+ "loss": 0.6698,
50
+ "rewards/accuracies": 0.612500011920929,
51
+ "rewards/chosen": 0.23909731209278107,
52
+ "rewards/margins": 0.10868903249502182,
53
+ "rewards/rejected": 0.13040827214717865,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.06837606837606838,
58
+ "grad_norm": 34.33646066636181,
59
+ "learning_rate": 9.996710299650301e-07,
60
+ "logits/chosen": -2.476440668106079,
61
+ "logits/rejected": -2.450225353240967,
62
+ "logps/chosen": -158.1311798095703,
63
+ "logps/rejected": -158.0066680908203,
64
+ "loss": 0.6613,
65
+ "rewards/accuracies": 0.6000000238418579,
66
+ "rewards/chosen": 0.4318675100803375,
67
+ "rewards/margins": 0.14549395442008972,
68
+ "rewards/rejected": 0.2863735556602478,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.08547008547008547,
73
+ "grad_norm": 33.16430522723429,
74
+ "learning_rate": 9.992599188865604e-07,
75
+ "logits/chosen": -2.3086318969726562,
76
+ "logits/rejected": -2.3104796409606934,
77
+ "logps/chosen": -150.59771728515625,
78
+ "logps/rejected": -156.85037231445312,
79
+ "loss": 0.6494,
80
+ "rewards/accuracies": 0.581250011920929,
81
+ "rewards/chosen": 0.5047669410705566,
82
+ "rewards/margins": 0.16554531455039978,
83
+ "rewards/rejected": 0.33922165632247925,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.10256410256410256,
88
+ "grad_norm": 34.52861424862365,
89
+ "learning_rate": 9.98684552745256e-07,
90
+ "logits/chosen": -2.217874050140381,
91
+ "logits/rejected": -2.2254481315612793,
92
+ "logps/chosen": -161.29412841796875,
93
+ "logps/rejected": -161.40841674804688,
94
+ "loss": 0.6295,
95
+ "rewards/accuracies": 0.625,
96
+ "rewards/chosen": 0.4176379144191742,
97
+ "rewards/margins": 0.26531916856765747,
98
+ "rewards/rejected": 0.15231874585151672,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.11965811965811966,
103
+ "grad_norm": 31.455117829218544,
104
+ "learning_rate": 9.979451208349055e-07,
105
+ "logits/chosen": -2.2608728408813477,
106
+ "logits/rejected": -2.246007204055786,
107
+ "logps/chosen": -171.71456909179688,
108
+ "logps/rejected": -174.46578979492188,
109
+ "loss": 0.6305,
110
+ "rewards/accuracies": 0.6499999761581421,
111
+ "rewards/chosen": -0.01912705972790718,
112
+ "rewards/margins": 0.31441593170166016,
113
+ "rewards/rejected": -0.33354294300079346,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 31.67318837058587,
119
+ "learning_rate": 9.970418664264595e-07,
120
+ "logits/chosen": -2.345672130584717,
121
+ "logits/rejected": -2.331491470336914,
122
+ "logps/chosen": -171.24766540527344,
123
+ "logps/rejected": -176.8189697265625,
124
+ "loss": 0.5989,
125
+ "rewards/accuracies": 0.699999988079071,
126
+ "rewards/chosen": -0.27867692708969116,
127
+ "rewards/margins": 0.5290472507476807,
128
+ "rewards/rejected": -0.8077241778373718,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.13675213675213677,
133
+ "eval_logits/chosen": -2.4102065563201904,
134
+ "eval_logits/rejected": -2.401230573654175,
135
+ "eval_logps/chosen": -162.36439514160156,
136
+ "eval_logps/rejected": -167.4954071044922,
137
+ "eval_loss": 0.6069236993789673,
138
+ "eval_rewards/accuracies": 0.6365384459495544,
139
+ "eval_rewards/chosen": -0.388705849647522,
140
+ "eval_rewards/margins": 0.47280558943748474,
141
+ "eval_rewards/rejected": -0.8615114688873291,
142
+ "eval_runtime": 509.918,
143
+ "eval_samples_per_second": 16.305,
144
+ "eval_steps_per_second": 0.255,
145
+ "step": 40
146
+ },
147
+ {
148
+ "epoch": 0.15384615384615385,
149
+ "grad_norm": 36.18313806223269,
150
+ "learning_rate": 9.95975086687994e-07,
151
+ "logits/chosen": -2.44050669670105,
152
+ "logits/rejected": -2.4460220336914062,
153
+ "logps/chosen": -163.82875061035156,
154
+ "logps/rejected": -167.35989379882812,
155
+ "loss": 0.6146,
156
+ "rewards/accuracies": 0.7124999761581421,
157
+ "rewards/chosen": -0.31098368763923645,
158
+ "rewards/margins": 0.46269193291664124,
159
+ "rewards/rejected": -0.7736755609512329,
160
+ "step": 45
161
+ },
162
+ {
163
+ "epoch": 0.17094017094017094,
164
+ "grad_norm": 31.13412274683678,
165
+ "learning_rate": 9.947451325869439e-07,
166
+ "logits/chosen": -2.501091718673706,
167
+ "logits/rejected": -2.4991250038146973,
168
+ "logps/chosen": -172.09686279296875,
169
+ "logps/rejected": -177.7747802734375,
170
+ "loss": 0.577,
171
+ "rewards/accuracies": 0.75,
172
+ "rewards/chosen": -0.212348073720932,
173
+ "rewards/margins": 0.6062799692153931,
174
+ "rewards/rejected": -0.8186280131340027,
175
+ "step": 50
176
+ },
177
+ {
178
+ "epoch": 0.18803418803418803,
179
+ "grad_norm": 31.508672436862835,
180
+ "learning_rate": 9.933524087746347e-07,
181
+ "logits/chosen": -2.437525510787964,
182
+ "logits/rejected": -2.4285693168640137,
183
+ "logps/chosen": -168.1316375732422,
184
+ "logps/rejected": -175.23193359375,
185
+ "loss": 0.571,
186
+ "rewards/accuracies": 0.75,
187
+ "rewards/chosen": -0.513076901435852,
188
+ "rewards/margins": 0.7702310681343079,
189
+ "rewards/rejected": -1.2833080291748047,
190
+ "step": 55
191
+ },
192
+ {
193
+ "epoch": 0.20512820512820512,
194
+ "grad_norm": 30.148068867306787,
195
+ "learning_rate": 9.917973734531549e-07,
196
+ "logits/chosen": -2.431530475616455,
197
+ "logits/rejected": -2.431729793548584,
198
+ "logps/chosen": -159.38168334960938,
199
+ "logps/rejected": -170.52500915527344,
200
+ "loss": 0.5762,
201
+ "rewards/accuracies": 0.699999988079071,
202
+ "rewards/chosen": -0.34855490922927856,
203
+ "rewards/margins": 0.5969334244728088,
204
+ "rewards/rejected": -0.9454883337020874,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.2222222222222222,
209
+ "grad_norm": 32.03814968183332,
210
+ "learning_rate": 9.90080538224607e-07,
211
+ "logits/chosen": -2.533193588256836,
212
+ "logits/rejected": -2.5252978801727295,
213
+ "logps/chosen": -157.30966186523438,
214
+ "logps/rejected": -166.26011657714844,
215
+ "loss": 0.5643,
216
+ "rewards/accuracies": 0.706250011920929,
217
+ "rewards/chosen": -0.007600936107337475,
218
+ "rewards/margins": 0.5010749697685242,
219
+ "rewards/rejected": -0.5086758732795715,
220
+ "step": 65
221
+ },
222
+ {
223
+ "epoch": 0.23931623931623933,
224
+ "grad_norm": 29.16308768569833,
225
+ "learning_rate": 9.882024679227938e-07,
226
+ "logits/chosen": -2.5899624824523926,
227
+ "logits/rejected": -2.5779967308044434,
228
+ "logps/chosen": -178.4553985595703,
229
+ "logps/rejected": -179.71542358398438,
230
+ "loss": 0.5464,
231
+ "rewards/accuracies": 0.699999988079071,
232
+ "rewards/chosen": -0.47189587354660034,
233
+ "rewards/margins": 0.8304598927497864,
234
+ "rewards/rejected": -1.3023556470870972,
235
+ "step": 70
236
+ },
237
+ {
238
+ "epoch": 0.2564102564102564,
239
+ "grad_norm": 28.918531347661485,
240
+ "learning_rate": 9.861637804273881e-07,
241
+ "logits/chosen": -2.578892469406128,
242
+ "logits/rejected": -2.5758416652679443,
243
+ "logps/chosen": -162.60537719726562,
244
+ "logps/rejected": -170.6789093017578,
245
+ "loss": 0.5553,
246
+ "rewards/accuracies": 0.6875,
247
+ "rewards/chosen": -0.45147842168807983,
248
+ "rewards/margins": 0.6994724273681641,
249
+ "rewards/rejected": -1.1509509086608887,
250
+ "step": 75
251
+ },
252
+ {
253
+ "epoch": 0.27350427350427353,
254
+ "grad_norm": 26.98866754941649,
255
+ "learning_rate": 9.83965146460653e-07,
256
+ "logits/chosen": -2.54936146736145,
257
+ "logits/rejected": -2.5406956672668457,
258
+ "logps/chosen": -168.81484985351562,
259
+ "logps/rejected": -179.770751953125,
260
+ "loss": 0.5452,
261
+ "rewards/accuracies": 0.6812499761581421,
262
+ "rewards/chosen": -0.6899678111076355,
263
+ "rewards/margins": 0.8549306988716125,
264
+ "rewards/rejected": -1.544898509979248,
265
+ "step": 80
266
+ },
267
+ {
268
+ "epoch": 0.27350427350427353,
269
+ "eval_logits/chosen": -2.53336238861084,
270
+ "eval_logits/rejected": -2.517695665359497,
271
+ "eval_logps/chosen": -167.28964233398438,
272
+ "eval_logps/rejected": -177.21824645996094,
273
+ "eval_loss": 0.5331124663352966,
274
+ "eval_rewards/accuracies": 0.7134615182876587,
275
+ "eval_rewards/chosen": -0.8812309503555298,
276
+ "eval_rewards/margins": 0.9525622725486755,
277
+ "eval_rewards/rejected": -1.8337931632995605,
278
+ "eval_runtime": 510.0922,
279
+ "eval_samples_per_second": 16.299,
280
+ "eval_steps_per_second": 0.255,
281
+ "step": 80
282
+ },
283
+ {
284
+ "epoch": 0.2905982905982906,
285
+ "grad_norm": 34.783908892421536,
286
+ "learning_rate": 9.816072893667758e-07,
287
+ "logits/chosen": -2.5432825088500977,
288
+ "logits/rejected": -2.5159504413604736,
289
+ "logps/chosen": -174.62197875976562,
290
+ "logps/rejected": -185.89413452148438,
291
+ "loss": 0.5581,
292
+ "rewards/accuracies": 0.7437499761581421,
293
+ "rewards/chosen": -1.0434839725494385,
294
+ "rewards/margins": 1.0283188819885254,
295
+ "rewards/rejected": -2.0718026161193848,
296
+ "step": 85
297
+ },
298
+ {
299
+ "epoch": 0.3076923076923077,
300
+ "grad_norm": 26.697686805838906,
301
+ "learning_rate": 9.790909848738904e-07,
302
+ "logits/chosen": -2.5102508068084717,
303
+ "logits/rejected": -2.5222485065460205,
304
+ "logps/chosen": -175.47544860839844,
305
+ "logps/rejected": -183.92678833007812,
306
+ "loss": 0.5208,
307
+ "rewards/accuracies": 0.637499988079071,
308
+ "rewards/chosen": -0.9199908971786499,
309
+ "rewards/margins": 0.8521744608879089,
310
+ "rewards/rejected": -1.7721655368804932,
311
+ "step": 90
312
+ },
313
+ {
314
+ "epoch": 0.3247863247863248,
315
+ "grad_norm": 30.125094604814798,
316
+ "learning_rate": 9.764170608388647e-07,
317
+ "logits/chosen": -2.514260768890381,
318
+ "logits/rejected": -2.4829812049865723,
319
+ "logps/chosen": -167.62655639648438,
320
+ "logps/rejected": -174.2395477294922,
321
+ "loss": 0.5242,
322
+ "rewards/accuracies": 0.7749999761581421,
323
+ "rewards/chosen": -0.6241778135299683,
324
+ "rewards/margins": 1.0742968320846558,
325
+ "rewards/rejected": -1.6984745264053345,
326
+ "step": 95
327
+ },
328
+ {
329
+ "epoch": 0.3418803418803419,
330
+ "grad_norm": 27.550843374580296,
331
+ "learning_rate": 9.735863969749371e-07,
332
+ "logits/chosen": -2.4171032905578613,
333
+ "logits/rejected": -2.381608486175537,
334
+ "logps/chosen": -177.05935668945312,
335
+ "logps/rejected": -188.4621124267578,
336
+ "loss": 0.5002,
337
+ "rewards/accuracies": 0.706250011920929,
338
+ "rewards/chosen": -0.7831762433052063,
339
+ "rewards/margins": 1.0672458410263062,
340
+ "rewards/rejected": -1.8504221439361572,
341
+ "step": 100
342
+ },
343
+ {
344
+ "epoch": 0.358974358974359,
345
+ "grad_norm": 30.39392617500016,
346
+ "learning_rate": 9.705999245622956e-07,
347
+ "logits/chosen": -2.3619236946105957,
348
+ "logits/rejected": -2.3391060829162598,
349
+ "logps/chosen": -170.48300170898438,
350
+ "logps/rejected": -183.28384399414062,
351
+ "loss": 0.5026,
352
+ "rewards/accuracies": 0.7124999761581421,
353
+ "rewards/chosen": -0.8889726400375366,
354
+ "rewards/margins": 0.9097515940666199,
355
+ "rewards/rejected": -1.7987244129180908,
356
+ "step": 105
357
+ },
358
+ {
359
+ "epoch": 0.37606837606837606,
360
+ "grad_norm": 26.741945030347612,
361
+ "learning_rate": 9.674586261416873e-07,
362
+ "logits/chosen": -2.2946972846984863,
363
+ "logits/rejected": -2.2440435886383057,
364
+ "logps/chosen": -179.06390380859375,
365
+ "logps/rejected": -188.00010681152344,
366
+ "loss": 0.5206,
367
+ "rewards/accuracies": 0.699999988079071,
368
+ "rewards/chosen": -0.6539386510848999,
369
+ "rewards/margins": 1.0372655391693115,
370
+ "rewards/rejected": -1.691204309463501,
371
+ "step": 110
372
+ },
373
+ {
374
+ "epoch": 0.39316239316239315,
375
+ "grad_norm": 33.116742735027486,
376
+ "learning_rate": 9.641635351911664e-07,
377
+ "logits/chosen": -2.218276262283325,
378
+ "logits/rejected": -2.18500018119812,
379
+ "logps/chosen": -171.17381286621094,
380
+ "logps/rejected": -183.25845336914062,
381
+ "loss": 0.4801,
382
+ "rewards/accuracies": 0.7437499761581421,
383
+ "rewards/chosen": -0.9279203414916992,
384
+ "rewards/margins": 1.2727015018463135,
385
+ "rewards/rejected": -2.200622081756592,
386
+ "step": 115
387
+ },
388
+ {
389
+ "epoch": 0.41025641025641024,
390
+ "grad_norm": 27.185641229760538,
391
+ "learning_rate": 9.607157357860821e-07,
392
+ "logits/chosen": -2.124584436416626,
393
+ "logits/rejected": -2.0961549282073975,
394
+ "logps/chosen": -189.48277282714844,
395
+ "logps/rejected": -203.43951416015625,
396
+ "loss": 0.5026,
397
+ "rewards/accuracies": 0.737500011920929,
398
+ "rewards/chosen": -1.2869656085968018,
399
+ "rewards/margins": 1.3039339780807495,
400
+ "rewards/rejected": -2.5908992290496826,
401
+ "step": 120
402
+ },
403
+ {
404
+ "epoch": 0.41025641025641024,
405
+ "eval_logits/chosen": -2.0268211364746094,
406
+ "eval_logits/rejected": -1.9764775037765503,
407
+ "eval_logps/chosen": -172.888671875,
408
+ "eval_logps/rejected": -185.58355712890625,
409
+ "eval_loss": 0.49246644973754883,
410
+ "eval_rewards/accuracies": 0.7442307472229004,
411
+ "eval_rewards/chosen": -1.441135048866272,
412
+ "eval_rewards/margins": 1.2291908264160156,
413
+ "eval_rewards/rejected": -2.670325756072998,
414
+ "eval_runtime": 510.1247,
415
+ "eval_samples_per_second": 16.298,
416
+ "eval_steps_per_second": 0.255,
417
+ "step": 120
418
+ }
419
+ ],
420
+ "logging_steps": 5,
421
+ "max_steps": 876,
422
+ "num_input_tokens_seen": 0,
423
+ "num_train_epochs": 3,
424
+ "save_steps": 40,
425
+ "stateful_callbacks": {
426
+ "TrainerControl": {
427
+ "args": {
428
+ "should_epoch_stop": false,
429
+ "should_evaluate": false,
430
+ "should_log": false,
431
+ "should_save": true,
432
+ "should_training_stop": false
433
+ },
434
+ "attributes": {}
435
+ }
436
+ },
437
+ "total_flos": 1414680891359232.0,
438
+ "train_batch_size": 8,
439
+ "trial_name": null,
440
+ "trial_params": null
441
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831d672014bf462253aa782d6da94e92dafa0a12ece6f1f8b7e68a5fb7e1420d
3
+ size 7096
checkpoint-160/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
checkpoint-160/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 4096,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 336,
11
+ 672
12
+ ],
13
+ [
14
+ 672,
15
+ 336
16
+ ],
17
+ [
18
+ 672,
19
+ 672
20
+ ],
21
+ [
22
+ 1008,
23
+ 336
24
+ ],
25
+ [
26
+ 336,
27
+ 1008
28
+ ]
29
+ ],
30
+ "image_seq_length": 576,
31
+ "image_token_index": 32000,
32
+ "model_type": "llava_next",
33
+ "projector_hidden_act": "gelu",
34
+ "text_config": {
35
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
36
+ "architectures": [
37
+ "MistralForCausalLM"
38
+ ],
39
+ "intermediate_size": 14336,
40
+ "max_position_embeddings": 32768,
41
+ "model_type": "mistral",
42
+ "num_key_value_heads": 8,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 1000000.0,
45
+ "sliding_window": null,
46
+ "torch_dtype": "bfloat16",
47
+ "vocab_size": 32064
48
+ },
49
+ "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.45.2",
52
+ "use_cache": false,
53
+ "use_image_newline_parameter": true,
54
+ "vision_config": {
55
+ "hidden_size": 1024,
56
+ "image_size": 336,
57
+ "intermediate_size": 4096,
58
+ "model_type": "clip_vision_model",
59
+ "num_attention_heads": 16,
60
+ "num_hidden_layers": 24,
61
+ "patch_size": 14,
62
+ "projection_dim": 768,
63
+ "vocab_size": 32000
64
+ },
65
+ "vision_feature_layer": -2,
66
+ "vision_feature_select_strategy": "default",
67
+ "vocab_size": 32064
68
+ }
checkpoint-160/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
+ }
checkpoint-160/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a747b93c27f3ae44d2f36d9ea1a764aa25460b3534c019cbf479e2e96191e6
3
+ size 4921618624
checkpoint-160/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f994ab8cd03e78333ac0908cb307f855ea88a6b788d2738ad637fa30c2832c5
3
+ size 4915917672
checkpoint-160/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d810c0106c87e44f7c396778f08cadcfc7b48dca94f7cdd4d0ed32564ad9eb5e
3
+ size 4915917680
checkpoint-160/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884f027e1a8b208cc9b67a84c0962d359deea451cafdc037008fc9b6cb58094c
3
+ size 380134008
checkpoint-160/model.safetensors.index.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15133495296
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
298
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
299
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
300
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
301
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
302
+ "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
303
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
304
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
305
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
316
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
317
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
322
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
323
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
324
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
325
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
326
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
327
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
328
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
329
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
330
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
331
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
332
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
333
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
334
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
335
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
336
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
337
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
342
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
343
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
344
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
345
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
346
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
347
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
348
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
349
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
350
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
351
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
352
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
400
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
401
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
406
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
407
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
408
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
432
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
433
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
434
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
435
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
436
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
437
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
438
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
439
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
440
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
441
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
444
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
445
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
693
+ }
694
+ }
checkpoint-160/preprocessor_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_grid_pinpoints": [
14
+ [
15
+ 336,
16
+ 672
17
+ ],
18
+ [
19
+ 672,
20
+ 336
21
+ ],
22
+ [
23
+ 672,
24
+ 672
25
+ ],
26
+ [
27
+ 1008,
28
+ 336
29
+ ],
30
+ [
31
+ 336,
32
+ 1008
33
+ ]
34
+ ],
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_processor_type": "LlavaNextImageProcessor",
41
+ "image_std": [
42
+ 0.26862954,
43
+ 0.26130258,
44
+ 0.27577711
45
+ ],
46
+ "processor_class": "LlavaNextProcessor",
47
+ "resample": 3,
48
+ "rescale_factor": 0.00392156862745098,
49
+ "size": {
50
+ "shortest_edge": 336
51
+ }
52
+ }
checkpoint-160/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-160/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-160/tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {
53
+ "image_token": "<image>"
54
+ },
55
+ "image_token": "<image>",
56
+ "legacy": true,
57
+ "max_length": null,
58
+ "model_max_length": 1000000000000000019884624838656,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "<pad>",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "processor_class": "LlavaNextProcessor",
64
+ "sp_model_kwargs": {},
65
+ "spaces_between_special_tokens": false,
66
+ "split_special_tokens": false,
67
+ "tokenizer_class": "LlamaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,577 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5470085470085471,
5
+ "eval_steps": 40,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017094017094017096,
13
+ "grad_norm": 35.038580788061665,
14
+ "learning_rate": 5e-07,
15
+ "logits/chosen": -2.7457876205444336,
16
+ "logits/rejected": -2.7444841861724854,
17
+ "logps/chosen": -164.26461791992188,
18
+ "logps/rejected": -170.55870056152344,
19
+ "loss": 0.6935,
20
+ "rewards/accuracies": 0.26875001192092896,
21
+ "rewards/chosen": 0.003455913159996271,
22
+ "rewards/margins": -0.0019886991940438747,
23
+ "rewards/rejected": 0.0054446132853627205,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.03418803418803419,
28
+ "grad_norm": 36.203903910498276,
29
+ "learning_rate": 1e-06,
30
+ "logits/chosen": -2.7106502056121826,
31
+ "logits/rejected": -2.716397523880005,
32
+ "logps/chosen": -171.80043029785156,
33
+ "logps/rejected": -165.20602416992188,
34
+ "loss": 0.6875,
35
+ "rewards/accuracies": 0.5062500238418579,
36
+ "rewards/chosen": 0.012000308372080326,
37
+ "rewards/margins": 0.0025437879376113415,
38
+ "rewards/rejected": 0.009456520900130272,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.05128205128205128,
43
+ "grad_norm": 33.9576577784673,
44
+ "learning_rate": 9.999177507263144e-07,
45
+ "logits/chosen": -2.651571750640869,
46
+ "logits/rejected": -2.629457473754883,
47
+ "logps/chosen": -174.04080200195312,
48
+ "logps/rejected": -174.0542755126953,
49
+ "loss": 0.6698,
50
+ "rewards/accuracies": 0.612500011920929,
51
+ "rewards/chosen": 0.23909731209278107,
52
+ "rewards/margins": 0.10868903249502182,
53
+ "rewards/rejected": 0.13040827214717865,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.06837606837606838,
58
+ "grad_norm": 34.33646066636181,
59
+ "learning_rate": 9.996710299650301e-07,
60
+ "logits/chosen": -2.476440668106079,
61
+ "logits/rejected": -2.450225353240967,
62
+ "logps/chosen": -158.1311798095703,
63
+ "logps/rejected": -158.0066680908203,
64
+ "loss": 0.6613,
65
+ "rewards/accuracies": 0.6000000238418579,
66
+ "rewards/chosen": 0.4318675100803375,
67
+ "rewards/margins": 0.14549395442008972,
68
+ "rewards/rejected": 0.2863735556602478,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.08547008547008547,
73
+ "grad_norm": 33.16430522723429,
74
+ "learning_rate": 9.992599188865604e-07,
75
+ "logits/chosen": -2.3086318969726562,
76
+ "logits/rejected": -2.3104796409606934,
77
+ "logps/chosen": -150.59771728515625,
78
+ "logps/rejected": -156.85037231445312,
79
+ "loss": 0.6494,
80
+ "rewards/accuracies": 0.581250011920929,
81
+ "rewards/chosen": 0.5047669410705566,
82
+ "rewards/margins": 0.16554531455039978,
83
+ "rewards/rejected": 0.33922165632247925,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.10256410256410256,
88
+ "grad_norm": 34.52861424862365,
89
+ "learning_rate": 9.98684552745256e-07,
90
+ "logits/chosen": -2.217874050140381,
91
+ "logits/rejected": -2.2254481315612793,
92
+ "logps/chosen": -161.29412841796875,
93
+ "logps/rejected": -161.40841674804688,
94
+ "loss": 0.6295,
95
+ "rewards/accuracies": 0.625,
96
+ "rewards/chosen": 0.4176379144191742,
97
+ "rewards/margins": 0.26531916856765747,
98
+ "rewards/rejected": 0.15231874585151672,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.11965811965811966,
103
+ "grad_norm": 31.455117829218544,
104
+ "learning_rate": 9.979451208349055e-07,
105
+ "logits/chosen": -2.2608728408813477,
106
+ "logits/rejected": -2.246007204055786,
107
+ "logps/chosen": -171.71456909179688,
108
+ "logps/rejected": -174.46578979492188,
109
+ "loss": 0.6305,
110
+ "rewards/accuracies": 0.6499999761581421,
111
+ "rewards/chosen": -0.01912705972790718,
112
+ "rewards/margins": 0.31441593170166016,
113
+ "rewards/rejected": -0.33354294300079346,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 31.67318837058587,
119
+ "learning_rate": 9.970418664264595e-07,
120
+ "logits/chosen": -2.345672130584717,
121
+ "logits/rejected": -2.331491470336914,
122
+ "logps/chosen": -171.24766540527344,
123
+ "logps/rejected": -176.8189697265625,
124
+ "loss": 0.5989,
125
+ "rewards/accuracies": 0.699999988079071,
126
+ "rewards/chosen": -0.27867692708969116,
127
+ "rewards/margins": 0.5290472507476807,
128
+ "rewards/rejected": -0.8077241778373718,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.13675213675213677,
133
+ "eval_logits/chosen": -2.4102065563201904,
134
+ "eval_logits/rejected": -2.401230573654175,
135
+ "eval_logps/chosen": -162.36439514160156,
136
+ "eval_logps/rejected": -167.4954071044922,
137
+ "eval_loss": 0.6069236993789673,
138
+ "eval_rewards/accuracies": 0.6365384459495544,
139
+ "eval_rewards/chosen": -0.388705849647522,
140
+ "eval_rewards/margins": 0.47280558943748474,
141
+ "eval_rewards/rejected": -0.8615114688873291,
142
+ "eval_runtime": 509.918,
143
+ "eval_samples_per_second": 16.305,
144
+ "eval_steps_per_second": 0.255,
145
+ "step": 40
146
+ },
147
+ {
148
+ "epoch": 0.15384615384615385,
149
+ "grad_norm": 36.18313806223269,
150
+ "learning_rate": 9.95975086687994e-07,
151
+ "logits/chosen": -2.44050669670105,
152
+ "logits/rejected": -2.4460220336914062,
153
+ "logps/chosen": -163.82875061035156,
154
+ "logps/rejected": -167.35989379882812,
155
+ "loss": 0.6146,
156
+ "rewards/accuracies": 0.7124999761581421,
157
+ "rewards/chosen": -0.31098368763923645,
158
+ "rewards/margins": 0.46269193291664124,
159
+ "rewards/rejected": -0.7736755609512329,
160
+ "step": 45
161
+ },
162
+ {
163
+ "epoch": 0.17094017094017094,
164
+ "grad_norm": 31.13412274683678,
165
+ "learning_rate": 9.947451325869439e-07,
166
+ "logits/chosen": -2.501091718673706,
167
+ "logits/rejected": -2.4991250038146973,
168
+ "logps/chosen": -172.09686279296875,
169
+ "logps/rejected": -177.7747802734375,
170
+ "loss": 0.577,
171
+ "rewards/accuracies": 0.75,
172
+ "rewards/chosen": -0.212348073720932,
173
+ "rewards/margins": 0.6062799692153931,
174
+ "rewards/rejected": -0.8186280131340027,
175
+ "step": 50
176
+ },
177
+ {
178
+ "epoch": 0.18803418803418803,
179
+ "grad_norm": 31.508672436862835,
180
+ "learning_rate": 9.933524087746347e-07,
181
+ "logits/chosen": -2.437525510787964,
182
+ "logits/rejected": -2.4285693168640137,
183
+ "logps/chosen": -168.1316375732422,
184
+ "logps/rejected": -175.23193359375,
185
+ "loss": 0.571,
186
+ "rewards/accuracies": 0.75,
187
+ "rewards/chosen": -0.513076901435852,
188
+ "rewards/margins": 0.7702310681343079,
189
+ "rewards/rejected": -1.2833080291748047,
190
+ "step": 55
191
+ },
192
+ {
193
+ "epoch": 0.20512820512820512,
194
+ "grad_norm": 30.148068867306787,
195
+ "learning_rate": 9.917973734531549e-07,
196
+ "logits/chosen": -2.431530475616455,
197
+ "logits/rejected": -2.431729793548584,
198
+ "logps/chosen": -159.38168334960938,
199
+ "logps/rejected": -170.52500915527344,
200
+ "loss": 0.5762,
201
+ "rewards/accuracies": 0.699999988079071,
202
+ "rewards/chosen": -0.34855490922927856,
203
+ "rewards/margins": 0.5969334244728088,
204
+ "rewards/rejected": -0.9454883337020874,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.2222222222222222,
209
+ "grad_norm": 32.03814968183332,
210
+ "learning_rate": 9.90080538224607e-07,
211
+ "logits/chosen": -2.533193588256836,
212
+ "logits/rejected": -2.5252978801727295,
213
+ "logps/chosen": -157.30966186523438,
214
+ "logps/rejected": -166.26011657714844,
215
+ "loss": 0.5643,
216
+ "rewards/accuracies": 0.706250011920929,
217
+ "rewards/chosen": -0.007600936107337475,
218
+ "rewards/margins": 0.5010749697685242,
219
+ "rewards/rejected": -0.5086758732795715,
220
+ "step": 65
221
+ },
222
+ {
223
+ "epoch": 0.23931623931623933,
224
+ "grad_norm": 29.16308768569833,
225
+ "learning_rate": 9.882024679227938e-07,
226
+ "logits/chosen": -2.5899624824523926,
227
+ "logits/rejected": -2.5779967308044434,
228
+ "logps/chosen": -178.4553985595703,
229
+ "logps/rejected": -179.71542358398438,
230
+ "loss": 0.5464,
231
+ "rewards/accuracies": 0.699999988079071,
232
+ "rewards/chosen": -0.47189587354660034,
233
+ "rewards/margins": 0.8304598927497864,
234
+ "rewards/rejected": -1.3023556470870972,
235
+ "step": 70
236
+ },
237
+ {
238
+ "epoch": 0.2564102564102564,
239
+ "grad_norm": 28.918531347661485,
240
+ "learning_rate": 9.861637804273881e-07,
241
+ "logits/chosen": -2.578892469406128,
242
+ "logits/rejected": -2.5758416652679443,
243
+ "logps/chosen": -162.60537719726562,
244
+ "logps/rejected": -170.6789093017578,
245
+ "loss": 0.5553,
246
+ "rewards/accuracies": 0.6875,
247
+ "rewards/chosen": -0.45147842168807983,
248
+ "rewards/margins": 0.6994724273681641,
249
+ "rewards/rejected": -1.1509509086608887,
250
+ "step": 75
251
+ },
252
+ {
253
+ "epoch": 0.27350427350427353,
254
+ "grad_norm": 26.98866754941649,
255
+ "learning_rate": 9.83965146460653e-07,
256
+ "logits/chosen": -2.54936146736145,
257
+ "logits/rejected": -2.5406956672668457,
258
+ "logps/chosen": -168.81484985351562,
259
+ "logps/rejected": -179.770751953125,
260
+ "loss": 0.5452,
261
+ "rewards/accuracies": 0.6812499761581421,
262
+ "rewards/chosen": -0.6899678111076355,
263
+ "rewards/margins": 0.8549306988716125,
264
+ "rewards/rejected": -1.544898509979248,
265
+ "step": 80
266
+ },
267
+ {
268
+ "epoch": 0.27350427350427353,
269
+ "eval_logits/chosen": -2.53336238861084,
270
+ "eval_logits/rejected": -2.517695665359497,
271
+ "eval_logps/chosen": -167.28964233398438,
272
+ "eval_logps/rejected": -177.21824645996094,
273
+ "eval_loss": 0.5331124663352966,
274
+ "eval_rewards/accuracies": 0.7134615182876587,
275
+ "eval_rewards/chosen": -0.8812309503555298,
276
+ "eval_rewards/margins": 0.9525622725486755,
277
+ "eval_rewards/rejected": -1.8337931632995605,
278
+ "eval_runtime": 510.0922,
279
+ "eval_samples_per_second": 16.299,
280
+ "eval_steps_per_second": 0.255,
281
+ "step": 80
282
+ },
283
+ {
284
+ "epoch": 0.2905982905982906,
285
+ "grad_norm": 34.783908892421536,
286
+ "learning_rate": 9.816072893667758e-07,
287
+ "logits/chosen": -2.5432825088500977,
288
+ "logits/rejected": -2.5159504413604736,
289
+ "logps/chosen": -174.62197875976562,
290
+ "logps/rejected": -185.89413452148438,
291
+ "loss": 0.5581,
292
+ "rewards/accuracies": 0.7437499761581421,
293
+ "rewards/chosen": -1.0434839725494385,
294
+ "rewards/margins": 1.0283188819885254,
295
+ "rewards/rejected": -2.0718026161193848,
296
+ "step": 85
297
+ },
298
+ {
299
+ "epoch": 0.3076923076923077,
300
+ "grad_norm": 26.697686805838906,
301
+ "learning_rate": 9.790909848738904e-07,
302
+ "logits/chosen": -2.5102508068084717,
303
+ "logits/rejected": -2.5222485065460205,
304
+ "logps/chosen": -175.47544860839844,
305
+ "logps/rejected": -183.92678833007812,
306
+ "loss": 0.5208,
307
+ "rewards/accuracies": 0.637499988079071,
308
+ "rewards/chosen": -0.9199908971786499,
309
+ "rewards/margins": 0.8521744608879089,
310
+ "rewards/rejected": -1.7721655368804932,
311
+ "step": 90
312
+ },
313
+ {
314
+ "epoch": 0.3247863247863248,
315
+ "grad_norm": 30.125094604814798,
316
+ "learning_rate": 9.764170608388647e-07,
317
+ "logits/chosen": -2.514260768890381,
318
+ "logits/rejected": -2.4829812049865723,
319
+ "logps/chosen": -167.62655639648438,
320
+ "logps/rejected": -174.2395477294922,
321
+ "loss": 0.5242,
322
+ "rewards/accuracies": 0.7749999761581421,
323
+ "rewards/chosen": -0.6241778135299683,
324
+ "rewards/margins": 1.0742968320846558,
325
+ "rewards/rejected": -1.6984745264053345,
326
+ "step": 95
327
+ },
328
+ {
329
+ "epoch": 0.3418803418803419,
330
+ "grad_norm": 27.550843374580296,
331
+ "learning_rate": 9.735863969749371e-07,
332
+ "logits/chosen": -2.4171032905578613,
333
+ "logits/rejected": -2.381608486175537,
334
+ "logps/chosen": -177.05935668945312,
335
+ "logps/rejected": -188.4621124267578,
336
+ "loss": 0.5002,
337
+ "rewards/accuracies": 0.706250011920929,
338
+ "rewards/chosen": -0.7831762433052063,
339
+ "rewards/margins": 1.0672458410263062,
340
+ "rewards/rejected": -1.8504221439361572,
341
+ "step": 100
342
+ },
343
+ {
344
+ "epoch": 0.358974358974359,
345
+ "grad_norm": 30.39392617500016,
346
+ "learning_rate": 9.705999245622956e-07,
347
+ "logits/chosen": -2.3619236946105957,
348
+ "logits/rejected": -2.3391060829162598,
349
+ "logps/chosen": -170.48300170898438,
350
+ "logps/rejected": -183.28384399414062,
351
+ "loss": 0.5026,
352
+ "rewards/accuracies": 0.7124999761581421,
353
+ "rewards/chosen": -0.8889726400375366,
354
+ "rewards/margins": 0.9097515940666199,
355
+ "rewards/rejected": -1.7987244129180908,
356
+ "step": 105
357
+ },
358
+ {
359
+ "epoch": 0.37606837606837606,
360
+ "grad_norm": 26.741945030347612,
361
+ "learning_rate": 9.674586261416873e-07,
362
+ "logits/chosen": -2.2946972846984863,
363
+ "logits/rejected": -2.2440435886383057,
364
+ "logps/chosen": -179.06390380859375,
365
+ "logps/rejected": -188.00010681152344,
366
+ "loss": 0.5206,
367
+ "rewards/accuracies": 0.699999988079071,
368
+ "rewards/chosen": -0.6539386510848999,
369
+ "rewards/margins": 1.0372655391693115,
370
+ "rewards/rejected": -1.691204309463501,
371
+ "step": 110
372
+ },
373
+ {
374
+ "epoch": 0.39316239316239315,
375
+ "grad_norm": 33.116742735027486,
376
+ "learning_rate": 9.641635351911664e-07,
377
+ "logits/chosen": -2.218276262283325,
378
+ "logits/rejected": -2.18500018119812,
379
+ "logps/chosen": -171.17381286621094,
380
+ "logps/rejected": -183.25845336914062,
381
+ "loss": 0.4801,
382
+ "rewards/accuracies": 0.7437499761581421,
383
+ "rewards/chosen": -0.9279203414916992,
384
+ "rewards/margins": 1.2727015018463135,
385
+ "rewards/rejected": -2.200622081756592,
386
+ "step": 115
387
+ },
388
+ {
389
+ "epoch": 0.41025641025641024,
390
+ "grad_norm": 27.185641229760538,
391
+ "learning_rate": 9.607157357860821e-07,
392
+ "logits/chosen": -2.124584436416626,
393
+ "logits/rejected": -2.0961549282073975,
394
+ "logps/chosen": -189.48277282714844,
395
+ "logps/rejected": -203.43951416015625,
396
+ "loss": 0.5026,
397
+ "rewards/accuracies": 0.737500011920929,
398
+ "rewards/chosen": -1.2869656085968018,
399
+ "rewards/margins": 1.3039339780807495,
400
+ "rewards/rejected": -2.5908992290496826,
401
+ "step": 120
402
+ },
403
+ {
404
+ "epoch": 0.41025641025641024,
405
+ "eval_logits/chosen": -2.0268211364746094,
406
+ "eval_logits/rejected": -1.9764775037765503,
407
+ "eval_logps/chosen": -172.888671875,
408
+ "eval_logps/rejected": -185.58355712890625,
409
+ "eval_loss": 0.49246644973754883,
410
+ "eval_rewards/accuracies": 0.7442307472229004,
411
+ "eval_rewards/chosen": -1.441135048866272,
412
+ "eval_rewards/margins": 1.2291908264160156,
413
+ "eval_rewards/rejected": -2.670325756072998,
414
+ "eval_runtime": 510.1247,
415
+ "eval_samples_per_second": 16.298,
416
+ "eval_steps_per_second": 0.255,
417
+ "step": 120
418
+ },
419
+ {
420
+ "epoch": 0.42735042735042733,
421
+ "grad_norm": 31.03461706328688,
422
+ "learning_rate": 9.571163622424225e-07,
423
+ "logits/chosen": -1.944964051246643,
424
+ "logits/rejected": -1.9178746938705444,
425
+ "logps/chosen": -175.3327178955078,
426
+ "logps/rejected": -188.2616729736328,
427
+ "loss": 0.5017,
428
+ "rewards/accuracies": 0.7124999761581421,
429
+ "rewards/chosen": -1.579502820968628,
430
+ "rewards/margins": 1.2485122680664062,
431
+ "rewards/rejected": -2.828014850616455,
432
+ "step": 125
433
+ },
434
+ {
435
+ "epoch": 0.4444444444444444,
436
+ "grad_norm": 29.080520770184428,
437
+ "learning_rate": 9.533665987436261e-07,
438
+ "logits/chosen": -1.8825464248657227,
439
+ "logits/rejected": -1.8078832626342773,
440
+ "logps/chosen": -178.3484649658203,
441
+ "logps/rejected": -197.55380249023438,
442
+ "loss": 0.4983,
443
+ "rewards/accuracies": 0.6937500238418579,
444
+ "rewards/chosen": -1.5868518352508545,
445
+ "rewards/margins": 1.2471343278884888,
446
+ "rewards/rejected": -2.8339860439300537,
447
+ "step": 130
448
+ },
449
+ {
450
+ "epoch": 0.46153846153846156,
451
+ "grad_norm": 28.903021536294002,
452
+ "learning_rate": 9.494676789509899e-07,
453
+ "logits/chosen": -1.8585374355316162,
454
+ "logits/rejected": -1.8128669261932373,
455
+ "logps/chosen": -178.5911407470703,
456
+ "logps/rejected": -195.90933227539062,
457
+ "loss": 0.492,
458
+ "rewards/accuracies": 0.7124999761581421,
459
+ "rewards/chosen": -1.2965319156646729,
460
+ "rewards/margins": 1.4173026084899902,
461
+ "rewards/rejected": -2.713834285736084,
462
+ "step": 135
463
+ },
464
+ {
465
+ "epoch": 0.47863247863247865,
466
+ "grad_norm": 27.5476391641307,
467
+ "learning_rate": 9.454208855977985e-07,
468
+ "logits/chosen": -1.920654296875,
469
+ "logits/rejected": -1.8412939310073853,
470
+ "logps/chosen": -179.1053924560547,
471
+ "logps/rejected": -196.11526489257812,
472
+ "loss": 0.4753,
473
+ "rewards/accuracies": 0.731249988079071,
474
+ "rewards/chosen": -1.5140180587768555,
475
+ "rewards/margins": 1.5388453006744385,
476
+ "rewards/rejected": -3.052863121032715,
477
+ "step": 140
478
+ },
479
+ {
480
+ "epoch": 0.49572649572649574,
481
+ "grad_norm": 30.03317842923354,
482
+ "learning_rate": 9.41227550067308e-07,
483
+ "logits/chosen": -1.9514515399932861,
484
+ "logits/rejected": -1.949883222579956,
485
+ "logps/chosen": -178.63250732421875,
486
+ "logps/rejected": -191.42721557617188,
487
+ "loss": 0.4803,
488
+ "rewards/accuracies": 0.7875000238418579,
489
+ "rewards/chosen": -1.513338327407837,
490
+ "rewards/margins": 1.4887291193008423,
491
+ "rewards/rejected": -3.0020670890808105,
492
+ "step": 145
493
+ },
494
+ {
495
+ "epoch": 0.5128205128205128,
496
+ "grad_norm": 30.28469957381902,
497
+ "learning_rate": 9.36889051954725e-07,
498
+ "logits/chosen": -2.0093894004821777,
499
+ "logits/rejected": -1.9657704830169678,
500
+ "logps/chosen": -180.35043334960938,
501
+ "logps/rejected": -197.2502899169922,
502
+ "loss": 0.4895,
503
+ "rewards/accuracies": 0.78125,
504
+ "rewards/chosen": -1.602224588394165,
505
+ "rewards/margins": 1.6883083581924438,
506
+ "rewards/rejected": -3.2905325889587402,
507
+ "step": 150
508
+ },
509
+ {
510
+ "epoch": 0.5299145299145299,
511
+ "grad_norm": 28.420242591686232,
512
+ "learning_rate": 9.324068186133245e-07,
513
+ "logits/chosen": -1.9976894855499268,
514
+ "logits/rejected": -1.9886022806167603,
515
+ "logps/chosen": -171.70602416992188,
516
+ "logps/rejected": -185.99795532226562,
517
+ "loss": 0.4608,
518
+ "rewards/accuracies": 0.793749988079071,
519
+ "rewards/chosen": -1.2952425479888916,
520
+ "rewards/margins": 1.7483227252960205,
521
+ "rewards/rejected": -3.043565034866333,
522
+ "step": 155
523
+ },
524
+ {
525
+ "epoch": 0.5470085470085471,
526
+ "grad_norm": 26.601543429998234,
527
+ "learning_rate": 9.277823246848536e-07,
528
+ "logits/chosen": -2.056879758834839,
529
+ "logits/rejected": -1.9998328685760498,
530
+ "logps/chosen": -186.3706817626953,
531
+ "logps/rejected": -196.63290405273438,
532
+ "loss": 0.4511,
533
+ "rewards/accuracies": 0.7124999761581421,
534
+ "rewards/chosen": -1.2312135696411133,
535
+ "rewards/margins": 1.352858304977417,
536
+ "rewards/rejected": -2.5840718746185303,
537
+ "step": 160
538
+ },
539
+ {
540
+ "epoch": 0.5470085470085471,
541
+ "eval_logits/chosen": -2.070892095565796,
542
+ "eval_logits/rejected": -2.0279953479766846,
543
+ "eval_logps/chosen": -171.76034545898438,
544
+ "eval_logps/rejected": -189.1643829345703,
545
+ "eval_loss": 0.4683005213737488,
546
+ "eval_rewards/accuracies": 0.762499988079071,
547
+ "eval_rewards/chosen": -1.328302264213562,
548
+ "eval_rewards/margins": 1.70010507106781,
549
+ "eval_rewards/rejected": -3.028407096862793,
550
+ "eval_runtime": 509.9565,
551
+ "eval_samples_per_second": 16.303,
552
+ "eval_steps_per_second": 0.255,
553
+ "step": 160
554
+ }
555
+ ],
556
+ "logging_steps": 5,
557
+ "max_steps": 876,
558
+ "num_input_tokens_seen": 0,
559
+ "num_train_epochs": 3,
560
+ "save_steps": 40,
561
+ "stateful_callbacks": {
562
+ "TrainerControl": {
563
+ "args": {
564
+ "should_epoch_stop": false,
565
+ "should_evaluate": false,
566
+ "should_log": false,
567
+ "should_save": true,
568
+ "should_training_stop": false
569
+ },
570
+ "attributes": {}
571
+ }
572
+ },
573
+ "total_flos": 1886397149478912.0,
574
+ "train_batch_size": 8,
575
+ "trial_name": null,
576
+ "trial_params": null
577
+ }
checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831d672014bf462253aa782d6da94e92dafa0a12ece6f1f8b7e68a5fb7e1420d
3
+ size 7096
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
checkpoint-200/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 4096,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 336,
11
+ 672
12
+ ],
13
+ [
14
+ 672,
15
+ 336
16
+ ],
17
+ [
18
+ 672,
19
+ 672
20
+ ],
21
+ [
22
+ 1008,
23
+ 336
24
+ ],
25
+ [
26
+ 336,
27
+ 1008
28
+ ]
29
+ ],
30
+ "image_seq_length": 576,
31
+ "image_token_index": 32000,
32
+ "model_type": "llava_next",
33
+ "projector_hidden_act": "gelu",
34
+ "text_config": {
35
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
36
+ "architectures": [
37
+ "MistralForCausalLM"
38
+ ],
39
+ "intermediate_size": 14336,
40
+ "max_position_embeddings": 32768,
41
+ "model_type": "mistral",
42
+ "num_key_value_heads": 8,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 1000000.0,
45
+ "sliding_window": null,
46
+ "torch_dtype": "bfloat16",
47
+ "vocab_size": 32064
48
+ },
49
+ "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.45.2",
52
+ "use_cache": false,
53
+ "use_image_newline_parameter": true,
54
+ "vision_config": {
55
+ "hidden_size": 1024,
56
+ "image_size": 336,
57
+ "intermediate_size": 4096,
58
+ "model_type": "clip_vision_model",
59
+ "num_attention_heads": 16,
60
+ "num_hidden_layers": 24,
61
+ "patch_size": 14,
62
+ "projection_dim": 768,
63
+ "vocab_size": 32000
64
+ },
65
+ "vision_feature_layer": -2,
66
+ "vision_feature_select_strategy": "default",
67
+ "vocab_size": 32064
68
+ }
checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
+ }
checkpoint-200/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e1f75431d2bfa4d16d00768065167b7c77e3f9b238b14b280f655202b56c47
3
+ size 4921618624
checkpoint-200/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d87d4b44a5b5618b4e1e40ec13156d5e9dbeb14d655702149139a22dfbf93b
3
+ size 4915917672
checkpoint-200/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dfac46c4e9c89769a96055f38ceb053100c1efcc1cbb79bc425751c49cd0baf
3
+ size 4915917680
checkpoint-200/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4ae8de4290ee97349a1fc61d9356c9e20cd6a318265045617d38ab94355977
3
+ size 380134008
checkpoint-200/model.safetensors.index.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15133495296
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
298
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
299
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
300
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
301
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
302
+ "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
303
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
304
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
305
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
316
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
317
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
322
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
323
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
324
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
325
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
326
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
327
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
328
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
329
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
330
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
331
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
332
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
333
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
334
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
335
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
336
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
337
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
342
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
343
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
344
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
345
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
346
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
347
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
348
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
349
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
350
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
351
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
352
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
400
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
401
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
406
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
407
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
408
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
432
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
433
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
434
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
435
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
436
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
437
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
438
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
439
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
440
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
441
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
444
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
445
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
693
+ }
694
+ }
checkpoint-200/preprocessor_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_grid_pinpoints": [
14
+ [
15
+ 336,
16
+ 672
17
+ ],
18
+ [
19
+ 672,
20
+ 336
21
+ ],
22
+ [
23
+ 672,
24
+ 672
25
+ ],
26
+ [
27
+ 1008,
28
+ 336
29
+ ],
30
+ [
31
+ 336,
32
+ 1008
33
+ ]
34
+ ],
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_processor_type": "LlavaNextImageProcessor",
41
+ "image_std": [
42
+ 0.26862954,
43
+ 0.26130258,
44
+ 0.27577711
45
+ ],
46
+ "processor_class": "LlavaNextProcessor",
47
+ "resample": 3,
48
+ "rescale_factor": 0.00392156862745098,
49
+ "size": {
50
+ "shortest_edge": 336
51
+ }
52
+ }
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '`[INST] `' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {
53
+ "image_token": "<image>"
54
+ },
55
+ "image_token": "<image>",
56
+ "legacy": true,
57
+ "max_length": null,
58
+ "model_max_length": 1000000000000000019884624838656,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "<pad>",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "processor_class": "LlavaNextProcessor",
64
+ "sp_model_kwargs": {},
65
+ "spaces_between_special_tokens": false,
66
+ "split_special_tokens": false,
67
+ "tokenizer_class": "LlamaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,713 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6837606837606838,
5
+ "eval_steps": 40,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017094017094017096,
13
+ "grad_norm": 35.038580788061665,
14
+ "learning_rate": 5e-07,
15
+ "logits/chosen": -2.7457876205444336,
16
+ "logits/rejected": -2.7444841861724854,
17
+ "logps/chosen": -164.26461791992188,
18
+ "logps/rejected": -170.55870056152344,
19
+ "loss": 0.6935,
20
+ "rewards/accuracies": 0.26875001192092896,
21
+ "rewards/chosen": 0.003455913159996271,
22
+ "rewards/margins": -0.0019886991940438747,
23
+ "rewards/rejected": 0.0054446132853627205,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.03418803418803419,
28
+ "grad_norm": 36.203903910498276,
29
+ "learning_rate": 1e-06,
30
+ "logits/chosen": -2.7106502056121826,
31
+ "logits/rejected": -2.716397523880005,
32
+ "logps/chosen": -171.80043029785156,
33
+ "logps/rejected": -165.20602416992188,
34
+ "loss": 0.6875,
35
+ "rewards/accuracies": 0.5062500238418579,
36
+ "rewards/chosen": 0.012000308372080326,
37
+ "rewards/margins": 0.0025437879376113415,
38
+ "rewards/rejected": 0.009456520900130272,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.05128205128205128,
43
+ "grad_norm": 33.9576577784673,
44
+ "learning_rate": 9.999177507263144e-07,
45
+ "logits/chosen": -2.651571750640869,
46
+ "logits/rejected": -2.629457473754883,
47
+ "logps/chosen": -174.04080200195312,
48
+ "logps/rejected": -174.0542755126953,
49
+ "loss": 0.6698,
50
+ "rewards/accuracies": 0.612500011920929,
51
+ "rewards/chosen": 0.23909731209278107,
52
+ "rewards/margins": 0.10868903249502182,
53
+ "rewards/rejected": 0.13040827214717865,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.06837606837606838,
58
+ "grad_norm": 34.33646066636181,
59
+ "learning_rate": 9.996710299650301e-07,
60
+ "logits/chosen": -2.476440668106079,
61
+ "logits/rejected": -2.450225353240967,
62
+ "logps/chosen": -158.1311798095703,
63
+ "logps/rejected": -158.0066680908203,
64
+ "loss": 0.6613,
65
+ "rewards/accuracies": 0.6000000238418579,
66
+ "rewards/chosen": 0.4318675100803375,
67
+ "rewards/margins": 0.14549395442008972,
68
+ "rewards/rejected": 0.2863735556602478,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.08547008547008547,
73
+ "grad_norm": 33.16430522723429,
74
+ "learning_rate": 9.992599188865604e-07,
75
+ "logits/chosen": -2.3086318969726562,
76
+ "logits/rejected": -2.3104796409606934,
77
+ "logps/chosen": -150.59771728515625,
78
+ "logps/rejected": -156.85037231445312,
79
+ "loss": 0.6494,
80
+ "rewards/accuracies": 0.581250011920929,
81
+ "rewards/chosen": 0.5047669410705566,
82
+ "rewards/margins": 0.16554531455039978,
83
+ "rewards/rejected": 0.33922165632247925,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.10256410256410256,
88
+ "grad_norm": 34.52861424862365,
89
+ "learning_rate": 9.98684552745256e-07,
90
+ "logits/chosen": -2.217874050140381,
91
+ "logits/rejected": -2.2254481315612793,
92
+ "logps/chosen": -161.29412841796875,
93
+ "logps/rejected": -161.40841674804688,
94
+ "loss": 0.6295,
95
+ "rewards/accuracies": 0.625,
96
+ "rewards/chosen": 0.4176379144191742,
97
+ "rewards/margins": 0.26531916856765747,
98
+ "rewards/rejected": 0.15231874585151672,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.11965811965811966,
103
+ "grad_norm": 31.455117829218544,
104
+ "learning_rate": 9.979451208349055e-07,
105
+ "logits/chosen": -2.2608728408813477,
106
+ "logits/rejected": -2.246007204055786,
107
+ "logps/chosen": -171.71456909179688,
108
+ "logps/rejected": -174.46578979492188,
109
+ "loss": 0.6305,
110
+ "rewards/accuracies": 0.6499999761581421,
111
+ "rewards/chosen": -0.01912705972790718,
112
+ "rewards/margins": 0.31441593170166016,
113
+ "rewards/rejected": -0.33354294300079346,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 31.67318837058587,
119
+ "learning_rate": 9.970418664264595e-07,
120
+ "logits/chosen": -2.345672130584717,
121
+ "logits/rejected": -2.331491470336914,
122
+ "logps/chosen": -171.24766540527344,
123
+ "logps/rejected": -176.8189697265625,
124
+ "loss": 0.5989,
125
+ "rewards/accuracies": 0.699999988079071,
126
+ "rewards/chosen": -0.27867692708969116,
127
+ "rewards/margins": 0.5290472507476807,
128
+ "rewards/rejected": -0.8077241778373718,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.13675213675213677,
133
+ "eval_logits/chosen": -2.4102065563201904,
134
+ "eval_logits/rejected": -2.401230573654175,
135
+ "eval_logps/chosen": -162.36439514160156,
136
+ "eval_logps/rejected": -167.4954071044922,
137
+ "eval_loss": 0.6069236993789673,
138
+ "eval_rewards/accuracies": 0.6365384459495544,
139
+ "eval_rewards/chosen": -0.388705849647522,
140
+ "eval_rewards/margins": 0.47280558943748474,
141
+ "eval_rewards/rejected": -0.8615114688873291,
142
+ "eval_runtime": 509.918,
143
+ "eval_samples_per_second": 16.305,
144
+ "eval_steps_per_second": 0.255,
145
+ "step": 40
146
+ },
147
+ {
148
+ "epoch": 0.15384615384615385,
149
+ "grad_norm": 36.18313806223269,
150
+ "learning_rate": 9.95975086687994e-07,
151
+ "logits/chosen": -2.44050669670105,
152
+ "logits/rejected": -2.4460220336914062,
153
+ "logps/chosen": -163.82875061035156,
154
+ "logps/rejected": -167.35989379882812,
155
+ "loss": 0.6146,
156
+ "rewards/accuracies": 0.7124999761581421,
157
+ "rewards/chosen": -0.31098368763923645,
158
+ "rewards/margins": 0.46269193291664124,
159
+ "rewards/rejected": -0.7736755609512329,
160
+ "step": 45
161
+ },
162
+ {
163
+ "epoch": 0.17094017094017094,
164
+ "grad_norm": 31.13412274683678,
165
+ "learning_rate": 9.947451325869439e-07,
166
+ "logits/chosen": -2.501091718673706,
167
+ "logits/rejected": -2.4991250038146973,
168
+ "logps/chosen": -172.09686279296875,
169
+ "logps/rejected": -177.7747802734375,
170
+ "loss": 0.577,
171
+ "rewards/accuracies": 0.75,
172
+ "rewards/chosen": -0.212348073720932,
173
+ "rewards/margins": 0.6062799692153931,
174
+ "rewards/rejected": -0.8186280131340027,
175
+ "step": 50
176
+ },
177
+ {
178
+ "epoch": 0.18803418803418803,
179
+ "grad_norm": 31.508672436862835,
180
+ "learning_rate": 9.933524087746347e-07,
181
+ "logits/chosen": -2.437525510787964,
182
+ "logits/rejected": -2.4285693168640137,
183
+ "logps/chosen": -168.1316375732422,
184
+ "logps/rejected": -175.23193359375,
185
+ "loss": 0.571,
186
+ "rewards/accuracies": 0.75,
187
+ "rewards/chosen": -0.513076901435852,
188
+ "rewards/margins": 0.7702310681343079,
189
+ "rewards/rejected": -1.2833080291748047,
190
+ "step": 55
191
+ },
192
+ {
193
+ "epoch": 0.20512820512820512,
194
+ "grad_norm": 30.148068867306787,
195
+ "learning_rate": 9.917973734531549e-07,
196
+ "logits/chosen": -2.431530475616455,
197
+ "logits/rejected": -2.431729793548584,
198
+ "logps/chosen": -159.38168334960938,
199
+ "logps/rejected": -170.52500915527344,
200
+ "loss": 0.5762,
201
+ "rewards/accuracies": 0.699999988079071,
202
+ "rewards/chosen": -0.34855490922927856,
203
+ "rewards/margins": 0.5969334244728088,
204
+ "rewards/rejected": -0.9454883337020874,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.2222222222222222,
209
+ "grad_norm": 32.03814968183332,
210
+ "learning_rate": 9.90080538224607e-07,
211
+ "logits/chosen": -2.533193588256836,
212
+ "logits/rejected": -2.5252978801727295,
213
+ "logps/chosen": -157.30966186523438,
214
+ "logps/rejected": -166.26011657714844,
215
+ "loss": 0.5643,
216
+ "rewards/accuracies": 0.706250011920929,
217
+ "rewards/chosen": -0.007600936107337475,
218
+ "rewards/margins": 0.5010749697685242,
219
+ "rewards/rejected": -0.5086758732795715,
220
+ "step": 65
221
+ },
222
+ {
223
+ "epoch": 0.23931623931623933,
224
+ "grad_norm": 29.16308768569833,
225
+ "learning_rate": 9.882024679227938e-07,
226
+ "logits/chosen": -2.5899624824523926,
227
+ "logits/rejected": -2.5779967308044434,
228
+ "logps/chosen": -178.4553985595703,
229
+ "logps/rejected": -179.71542358398438,
230
+ "loss": 0.5464,
231
+ "rewards/accuracies": 0.699999988079071,
232
+ "rewards/chosen": -0.47189587354660034,
233
+ "rewards/margins": 0.8304598927497864,
234
+ "rewards/rejected": -1.3023556470870972,
235
+ "step": 70
236
+ },
237
+ {
238
+ "epoch": 0.2564102564102564,
239
+ "grad_norm": 28.918531347661485,
240
+ "learning_rate": 9.861637804273881e-07,
241
+ "logits/chosen": -2.578892469406128,
242
+ "logits/rejected": -2.5758416652679443,
243
+ "logps/chosen": -162.60537719726562,
244
+ "logps/rejected": -170.6789093017578,
245
+ "loss": 0.5553,
246
+ "rewards/accuracies": 0.6875,
247
+ "rewards/chosen": -0.45147842168807983,
248
+ "rewards/margins": 0.6994724273681641,
249
+ "rewards/rejected": -1.1509509086608887,
250
+ "step": 75
251
+ },
252
+ {
253
+ "epoch": 0.27350427350427353,
254
+ "grad_norm": 26.98866754941649,
255
+ "learning_rate": 9.83965146460653e-07,
256
+ "logits/chosen": -2.54936146736145,
257
+ "logits/rejected": -2.5406956672668457,
258
+ "logps/chosen": -168.81484985351562,
259
+ "logps/rejected": -179.770751953125,
260
+ "loss": 0.5452,
261
+ "rewards/accuracies": 0.6812499761581421,
262
+ "rewards/chosen": -0.6899678111076355,
263
+ "rewards/margins": 0.8549306988716125,
264
+ "rewards/rejected": -1.544898509979248,
265
+ "step": 80
266
+ },
267
+ {
268
+ "epoch": 0.27350427350427353,
269
+ "eval_logits/chosen": -2.53336238861084,
270
+ "eval_logits/rejected": -2.517695665359497,
271
+ "eval_logps/chosen": -167.28964233398438,
272
+ "eval_logps/rejected": -177.21824645996094,
273
+ "eval_loss": 0.5331124663352966,
274
+ "eval_rewards/accuracies": 0.7134615182876587,
275
+ "eval_rewards/chosen": -0.8812309503555298,
276
+ "eval_rewards/margins": 0.9525622725486755,
277
+ "eval_rewards/rejected": -1.8337931632995605,
278
+ "eval_runtime": 510.0922,
279
+ "eval_samples_per_second": 16.299,
280
+ "eval_steps_per_second": 0.255,
281
+ "step": 80
282
+ },
283
+ {
284
+ "epoch": 0.2905982905982906,
285
+ "grad_norm": 34.783908892421536,
286
+ "learning_rate": 9.816072893667758e-07,
287
+ "logits/chosen": -2.5432825088500977,
288
+ "logits/rejected": -2.5159504413604736,
289
+ "logps/chosen": -174.62197875976562,
290
+ "logps/rejected": -185.89413452148438,
291
+ "loss": 0.5581,
292
+ "rewards/accuracies": 0.7437499761581421,
293
+ "rewards/chosen": -1.0434839725494385,
294
+ "rewards/margins": 1.0283188819885254,
295
+ "rewards/rejected": -2.0718026161193848,
296
+ "step": 85
297
+ },
298
+ {
299
+ "epoch": 0.3076923076923077,
300
+ "grad_norm": 26.697686805838906,
301
+ "learning_rate": 9.790909848738904e-07,
302
+ "logits/chosen": -2.5102508068084717,
303
+ "logits/rejected": -2.5222485065460205,
304
+ "logps/chosen": -175.47544860839844,
305
+ "logps/rejected": -183.92678833007812,
306
+ "loss": 0.5208,
307
+ "rewards/accuracies": 0.637499988079071,
308
+ "rewards/chosen": -0.9199908971786499,
309
+ "rewards/margins": 0.8521744608879089,
310
+ "rewards/rejected": -1.7721655368804932,
311
+ "step": 90
312
+ },
313
+ {
314
+ "epoch": 0.3247863247863248,
315
+ "grad_norm": 30.125094604814798,
316
+ "learning_rate": 9.764170608388647e-07,
317
+ "logits/chosen": -2.514260768890381,
318
+ "logits/rejected": -2.4829812049865723,
319
+ "logps/chosen": -167.62655639648438,
320
+ "logps/rejected": -174.2395477294922,
321
+ "loss": 0.5242,
322
+ "rewards/accuracies": 0.7749999761581421,
323
+ "rewards/chosen": -0.6241778135299683,
324
+ "rewards/margins": 1.0742968320846558,
325
+ "rewards/rejected": -1.6984745264053345,
326
+ "step": 95
327
+ },
328
+ {
329
+ "epoch": 0.3418803418803419,
330
+ "grad_norm": 27.550843374580296,
331
+ "learning_rate": 9.735863969749371e-07,
332
+ "logits/chosen": -2.4171032905578613,
333
+ "logits/rejected": -2.381608486175537,
334
+ "logps/chosen": -177.05935668945312,
335
+ "logps/rejected": -188.4621124267578,
336
+ "loss": 0.5002,
337
+ "rewards/accuracies": 0.706250011920929,
338
+ "rewards/chosen": -0.7831762433052063,
339
+ "rewards/margins": 1.0672458410263062,
340
+ "rewards/rejected": -1.8504221439361572,
341
+ "step": 100
342
+ },
343
+ {
344
+ "epoch": 0.358974358974359,
345
+ "grad_norm": 30.39392617500016,
346
+ "learning_rate": 9.705999245622956e-07,
347
+ "logits/chosen": -2.3619236946105957,
348
+ "logits/rejected": -2.3391060829162598,
349
+ "logps/chosen": -170.48300170898438,
350
+ "logps/rejected": -183.28384399414062,
351
+ "loss": 0.5026,
352
+ "rewards/accuracies": 0.7124999761581421,
353
+ "rewards/chosen": -0.8889726400375366,
354
+ "rewards/margins": 0.9097515940666199,
355
+ "rewards/rejected": -1.7987244129180908,
356
+ "step": 105
357
+ },
358
+ {
359
+ "epoch": 0.37606837606837606,
360
+ "grad_norm": 26.741945030347612,
361
+ "learning_rate": 9.674586261416873e-07,
362
+ "logits/chosen": -2.2946972846984863,
363
+ "logits/rejected": -2.2440435886383057,
364
+ "logps/chosen": -179.06390380859375,
365
+ "logps/rejected": -188.00010681152344,
366
+ "loss": 0.5206,
367
+ "rewards/accuracies": 0.699999988079071,
368
+ "rewards/chosen": -0.6539386510848999,
369
+ "rewards/margins": 1.0372655391693115,
370
+ "rewards/rejected": -1.691204309463501,
371
+ "step": 110
372
+ },
373
+ {
374
+ "epoch": 0.39316239316239315,
375
+ "grad_norm": 33.116742735027486,
376
+ "learning_rate": 9.641635351911664e-07,
377
+ "logits/chosen": -2.218276262283325,
378
+ "logits/rejected": -2.18500018119812,
379
+ "logps/chosen": -171.17381286621094,
380
+ "logps/rejected": -183.25845336914062,
381
+ "loss": 0.4801,
382
+ "rewards/accuracies": 0.7437499761581421,
383
+ "rewards/chosen": -0.9279203414916992,
384
+ "rewards/margins": 1.2727015018463135,
385
+ "rewards/rejected": -2.200622081756592,
386
+ "step": 115
387
+ },
388
+ {
389
+ "epoch": 0.41025641025641024,
390
+ "grad_norm": 27.185641229760538,
391
+ "learning_rate": 9.607157357860821e-07,
392
+ "logits/chosen": -2.124584436416626,
393
+ "logits/rejected": -2.0961549282073975,
394
+ "logps/chosen": -189.48277282714844,
395
+ "logps/rejected": -203.43951416015625,
396
+ "loss": 0.5026,
397
+ "rewards/accuracies": 0.737500011920929,
398
+ "rewards/chosen": -1.2869656085968018,
399
+ "rewards/margins": 1.3039339780807495,
400
+ "rewards/rejected": -2.5908992290496826,
401
+ "step": 120
402
+ },
403
+ {
404
+ "epoch": 0.41025641025641024,
405
+ "eval_logits/chosen": -2.0268211364746094,
406
+ "eval_logits/rejected": -1.9764775037765503,
407
+ "eval_logps/chosen": -172.888671875,
408
+ "eval_logps/rejected": -185.58355712890625,
409
+ "eval_loss": 0.49246644973754883,
410
+ "eval_rewards/accuracies": 0.7442307472229004,
411
+ "eval_rewards/chosen": -1.441135048866272,
412
+ "eval_rewards/margins": 1.2291908264160156,
413
+ "eval_rewards/rejected": -2.670325756072998,
414
+ "eval_runtime": 510.1247,
415
+ "eval_samples_per_second": 16.298,
416
+ "eval_steps_per_second": 0.255,
417
+ "step": 120
418
+ },
419
+ {
420
+ "epoch": 0.42735042735042733,
421
+ "grad_norm": 31.03461706328688,
422
+ "learning_rate": 9.571163622424225e-07,
423
+ "logits/chosen": -1.944964051246643,
424
+ "logits/rejected": -1.9178746938705444,
425
+ "logps/chosen": -175.3327178955078,
426
+ "logps/rejected": -188.2616729736328,
427
+ "loss": 0.5017,
428
+ "rewards/accuracies": 0.7124999761581421,
429
+ "rewards/chosen": -1.579502820968628,
430
+ "rewards/margins": 1.2485122680664062,
431
+ "rewards/rejected": -2.828014850616455,
432
+ "step": 125
433
+ },
434
+ {
435
+ "epoch": 0.4444444444444444,
436
+ "grad_norm": 29.080520770184428,
437
+ "learning_rate": 9.533665987436261e-07,
438
+ "logits/chosen": -1.8825464248657227,
439
+ "logits/rejected": -1.8078832626342773,
440
+ "logps/chosen": -178.3484649658203,
441
+ "logps/rejected": -197.55380249023438,
442
+ "loss": 0.4983,
443
+ "rewards/accuracies": 0.6937500238418579,
444
+ "rewards/chosen": -1.5868518352508545,
445
+ "rewards/margins": 1.2471343278884888,
446
+ "rewards/rejected": -2.8339860439300537,
447
+ "step": 130
448
+ },
449
+ {
450
+ "epoch": 0.46153846153846156,
451
+ "grad_norm": 28.903021536294002,
452
+ "learning_rate": 9.494676789509899e-07,
453
+ "logits/chosen": -1.8585374355316162,
454
+ "logits/rejected": -1.8128669261932373,
455
+ "logps/chosen": -178.5911407470703,
456
+ "logps/rejected": -195.90933227539062,
457
+ "loss": 0.492,
458
+ "rewards/accuracies": 0.7124999761581421,
459
+ "rewards/chosen": -1.2965319156646729,
460
+ "rewards/margins": 1.4173026084899902,
461
+ "rewards/rejected": -2.713834285736084,
462
+ "step": 135
463
+ },
464
+ {
465
+ "epoch": 0.47863247863247865,
466
+ "grad_norm": 27.5476391641307,
467
+ "learning_rate": 9.454208855977985e-07,
468
+ "logits/chosen": -1.920654296875,
469
+ "logits/rejected": -1.8412939310073853,
470
+ "logps/chosen": -179.1053924560547,
471
+ "logps/rejected": -196.11526489257812,
472
+ "loss": 0.4753,
473
+ "rewards/accuracies": 0.731249988079071,
474
+ "rewards/chosen": -1.5140180587768555,
475
+ "rewards/margins": 1.5388453006744385,
476
+ "rewards/rejected": -3.052863121032715,
477
+ "step": 140
478
+ },
479
+ {
480
+ "epoch": 0.49572649572649574,
481
+ "grad_norm": 30.03317842923354,
482
+ "learning_rate": 9.41227550067308e-07,
483
+ "logits/chosen": -1.9514515399932861,
484
+ "logits/rejected": -1.949883222579956,
485
+ "logps/chosen": -178.63250732421875,
486
+ "logps/rejected": -191.42721557617188,
487
+ "loss": 0.4803,
488
+ "rewards/accuracies": 0.7875000238418579,
489
+ "rewards/chosen": -1.513338327407837,
490
+ "rewards/margins": 1.4887291193008423,
491
+ "rewards/rejected": -3.0020670890808105,
492
+ "step": 145
493
+ },
494
+ {
495
+ "epoch": 0.5128205128205128,
496
+ "grad_norm": 30.28469957381902,
497
+ "learning_rate": 9.36889051954725e-07,
498
+ "logits/chosen": -2.0093894004821777,
499
+ "logits/rejected": -1.9657704830169678,
500
+ "logps/chosen": -180.35043334960938,
501
+ "logps/rejected": -197.2502899169922,
502
+ "loss": 0.4895,
503
+ "rewards/accuracies": 0.78125,
504
+ "rewards/chosen": -1.602224588394165,
505
+ "rewards/margins": 1.6883083581924438,
506
+ "rewards/rejected": -3.2905325889587402,
507
+ "step": 150
508
+ },
509
+ {
510
+ "epoch": 0.5299145299145299,
511
+ "grad_norm": 28.420242591686232,
512
+ "learning_rate": 9.324068186133245e-07,
513
+ "logits/chosen": -1.9976894855499268,
514
+ "logits/rejected": -1.9886022806167603,
515
+ "logps/chosen": -171.70602416992188,
516
+ "logps/rejected": -185.99795532226562,
517
+ "loss": 0.4608,
518
+ "rewards/accuracies": 0.793749988079071,
519
+ "rewards/chosen": -1.2952425479888916,
520
+ "rewards/margins": 1.7483227252960205,
521
+ "rewards/rejected": -3.043565034866333,
522
+ "step": 155
523
+ },
524
+ {
525
+ "epoch": 0.5470085470085471,
526
+ "grad_norm": 26.601543429998234,
527
+ "learning_rate": 9.277823246848536e-07,
528
+ "logits/chosen": -2.056879758834839,
529
+ "logits/rejected": -1.9998328685760498,
530
+ "logps/chosen": -186.3706817626953,
531
+ "logps/rejected": -196.63290405273438,
532
+ "loss": 0.4511,
533
+ "rewards/accuracies": 0.7124999761581421,
534
+ "rewards/chosen": -1.2312135696411133,
535
+ "rewards/margins": 1.352858304977417,
536
+ "rewards/rejected": -2.5840718746185303,
537
+ "step": 160
538
+ },
539
+ {
540
+ "epoch": 0.5470085470085471,
541
+ "eval_logits/chosen": -2.070892095565796,
542
+ "eval_logits/rejected": -2.0279953479766846,
543
+ "eval_logps/chosen": -171.76034545898438,
544
+ "eval_logps/rejected": -189.1643829345703,
545
+ "eval_loss": 0.4683005213737488,
546
+ "eval_rewards/accuracies": 0.762499988079071,
547
+ "eval_rewards/chosen": -1.328302264213562,
548
+ "eval_rewards/margins": 1.70010507106781,
549
+ "eval_rewards/rejected": -3.028407096862793,
550
+ "eval_runtime": 509.9565,
551
+ "eval_samples_per_second": 16.303,
552
+ "eval_steps_per_second": 0.255,
553
+ "step": 160
554
+ },
555
+ {
556
+ "epoch": 0.5641025641025641,
557
+ "grad_norm": 41.76296476638838,
558
+ "learning_rate": 9.230170916143793e-07,
559
+ "logits/chosen": -2.1190731525421143,
560
+ "logits/rejected": -2.083359956741333,
561
+ "logps/chosen": -176.87539672851562,
562
+ "logps/rejected": -198.44384765625,
563
+ "loss": 0.4944,
564
+ "rewards/accuracies": 0.7562500238418579,
565
+ "rewards/chosen": -1.2975060939788818,
566
+ "rewards/margins": 1.6890850067138672,
567
+ "rewards/rejected": -2.98659086227417,
568
+ "step": 165
569
+ },
570
+ {
571
+ "epoch": 0.5811965811965812,
572
+ "grad_norm": 28.83194976337172,
573
+ "learning_rate": 9.181126871497378e-07,
574
+ "logits/chosen": -2.175851583480835,
575
+ "logits/rejected": -2.1391243934631348,
576
+ "logps/chosen": -178.2881317138672,
577
+ "logps/rejected": -197.88473510742188,
578
+ "loss": 0.4813,
579
+ "rewards/accuracies": 0.78125,
580
+ "rewards/chosen": -1.2544641494750977,
581
+ "rewards/margins": 1.7747846841812134,
582
+ "rewards/rejected": -3.0292489528656006,
583
+ "step": 170
584
+ },
585
+ {
586
+ "epoch": 0.5982905982905983,
587
+ "grad_norm": 30.93659066586097,
588
+ "learning_rate": 9.130707248257491e-07,
589
+ "logits/chosen": -2.313814640045166,
590
+ "logits/rejected": -2.2677135467529297,
591
+ "logps/chosen": -170.06781005859375,
592
+ "logps/rejected": -177.8175811767578,
593
+ "loss": 0.4863,
594
+ "rewards/accuracies": 0.768750011920929,
595
+ "rewards/chosen": -1.0524061918258667,
596
+ "rewards/margins": 1.3644572496414185,
597
+ "rewards/rejected": -2.416863441467285,
598
+ "step": 175
599
+ },
600
+ {
601
+ "epoch": 0.6153846153846154,
602
+ "grad_norm": 25.018999438635433,
603
+ "learning_rate": 9.078928634333698e-07,
604
+ "logits/chosen": -2.302171230316162,
605
+ "logits/rejected": -2.2788572311401367,
606
+ "logps/chosen": -179.72390747070312,
607
+ "logps/rejected": -197.12283325195312,
608
+ "loss": 0.4553,
609
+ "rewards/accuracies": 0.8062499761581421,
610
+ "rewards/chosen": -0.6731274724006653,
611
+ "rewards/margins": 1.6728944778442383,
612
+ "rewards/rejected": -2.346021890640259,
613
+ "step": 180
614
+ },
615
+ {
616
+ "epoch": 0.6324786324786325,
617
+ "grad_norm": 28.576400660174777,
618
+ "learning_rate": 9.025808064739549e-07,
619
+ "logits/chosen": -2.2794651985168457,
620
+ "logits/rejected": -2.2391860485076904,
621
+ "logps/chosen": -175.87045288085938,
622
+ "logps/rejected": -189.4848175048828,
623
+ "loss": 0.4854,
624
+ "rewards/accuracies": 0.7562500238418579,
625
+ "rewards/chosen": -0.8901998400688171,
626
+ "rewards/margins": 1.4675487279891968,
627
+ "rewards/rejected": -2.357748508453369,
628
+ "step": 185
629
+ },
630
+ {
631
+ "epoch": 0.6495726495726496,
632
+ "grad_norm": 25.73471562251865,
633
+ "learning_rate": 8.971363015988113e-07,
634
+ "logits/chosen": -2.1966824531555176,
635
+ "logits/rejected": -2.1603925228118896,
636
+ "logps/chosen": -172.0600128173828,
637
+ "logps/rejected": -191.96176147460938,
638
+ "loss": 0.4681,
639
+ "rewards/accuracies": 0.7562500238418579,
640
+ "rewards/chosen": -0.9620615243911743,
641
+ "rewards/margins": 1.4954371452331543,
642
+ "rewards/rejected": -2.457498550415039,
643
+ "step": 190
644
+ },
645
+ {
646
+ "epoch": 0.6666666666666666,
647
+ "grad_norm": 34.912982133976655,
648
+ "learning_rate": 8.91561140034225e-07,
649
+ "logits/chosen": -2.1389029026031494,
650
+ "logits/rejected": -2.0825791358947754,
651
+ "logps/chosen": -174.3153839111328,
652
+ "logps/rejected": -194.2677459716797,
653
+ "loss": 0.4935,
654
+ "rewards/accuracies": 0.7437499761581421,
655
+ "rewards/chosen": -1.4726169109344482,
656
+ "rewards/margins": 1.4599871635437012,
657
+ "rewards/rejected": -2.9326040744781494,
658
+ "step": 195
659
+ },
660
+ {
661
+ "epoch": 0.6837606837606838,
662
+ "grad_norm": 25.756167591259292,
663
+ "learning_rate": 8.858571559921537e-07,
664
+ "logits/chosen": -2.135298013687134,
665
+ "logits/rejected": -2.067862033843994,
666
+ "logps/chosen": -178.73361206054688,
667
+ "logps/rejected": -193.21209716796875,
668
+ "loss": 0.4562,
669
+ "rewards/accuracies": 0.7562500238418579,
670
+ "rewards/chosen": -1.452704668045044,
671
+ "rewards/margins": 1.6391651630401611,
672
+ "rewards/rejected": -3.091869831085205,
673
+ "step": 200
674
+ },
675
+ {
676
+ "epoch": 0.6837606837606838,
677
+ "eval_logits/chosen": -2.1462392807006836,
678
+ "eval_logits/rejected": -2.1028637886047363,
679
+ "eval_logps/chosen": -173.41998291015625,
680
+ "eval_logps/rejected": -191.55532836914062,
681
+ "eval_loss": 0.4528014361858368,
682
+ "eval_rewards/accuracies": 0.7567307949066162,
683
+ "eval_rewards/chosen": -1.4942626953125,
684
+ "eval_rewards/margins": 1.7732419967651367,
685
+ "eval_rewards/rejected": -3.2675046920776367,
686
+ "eval_runtime": 510.9487,
687
+ "eval_samples_per_second": 16.272,
688
+ "eval_steps_per_second": 0.254,
689
+ "step": 200
690
+ }
691
+ ],
692
+ "logging_steps": 5,
693
+ "max_steps": 876,
694
+ "num_input_tokens_seen": 0,
695
+ "num_train_epochs": 3,
696
+ "save_steps": 40,
697
+ "stateful_callbacks": {
698
+ "TrainerControl": {
699
+ "args": {
700
+ "should_epoch_stop": false,
701
+ "should_evaluate": false,
702
+ "should_log": false,
703
+ "should_save": true,
704
+ "should_training_stop": false
705
+ },
706
+ "attributes": {}
707
+ }
708
+ },
709
+ "total_flos": 2358113407598592.0,
710
+ "train_batch_size": 8,
711
+ "trial_name": null,
712
+ "trial_params": null
713
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831d672014bf462253aa782d6da94e92dafa0a12ece6f1f8b7e68a5fb7e1420d
3
+ size 7096
checkpoint-240/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32001
4
+ }
checkpoint-240/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 4096,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 336,
11
+ 672
12
+ ],
13
+ [
14
+ 672,
15
+ 336
16
+ ],
17
+ [
18
+ 672,
19
+ 672
20
+ ],
21
+ [
22
+ 1008,
23
+ 336
24
+ ],
25
+ [
26
+ 336,
27
+ 1008
28
+ ]
29
+ ],
30
+ "image_seq_length": 576,
31
+ "image_token_index": 32000,
32
+ "model_type": "llava_next",
33
+ "projector_hidden_act": "gelu",
34
+ "text_config": {
35
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
36
+ "architectures": [
37
+ "MistralForCausalLM"
38
+ ],
39
+ "intermediate_size": 14336,
40
+ "max_position_embeddings": 32768,
41
+ "model_type": "mistral",
42
+ "num_key_value_heads": 8,
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 1000000.0,
45
+ "sliding_window": null,
46
+ "torch_dtype": "bfloat16",
47
+ "vocab_size": 32064
48
+ },
49
+ "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
+ "transformers_version": "4.45.2",
52
+ "use_cache": false,
53
+ "use_image_newline_parameter": true,
54
+ "vision_config": {
55
+ "hidden_size": 1024,
56
+ "image_size": 336,
57
+ "intermediate_size": 4096,
58
+ "model_type": "clip_vision_model",
59
+ "num_attention_heads": 16,
60
+ "num_hidden_layers": 24,
61
+ "patch_size": 14,
62
+ "projection_dim": 768,
63
+ "vocab_size": 32000
64
+ },
65
+ "vision_feature_layer": -2,
66
+ "vision_feature_select_strategy": "default",
67
+ "vocab_size": 32064
68
+ }