Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: other
+base_model: llava-hf/llava-v1.6-mistral-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: AA_text_image_to_text
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# AA_text_image_to_text
+
+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 AA_text_image_to_text dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4527
+- Rewards/chosen: -0.6857
+- Rewards/rejected: -4.3940
+- Rewards/accuracies: 0.8165
+- Rewards/margins: 3.7083
+- Logps/rejected: -242.1480
+- Logps/chosen: -207.1762
+- Logits/rejected: -2.3240
+- Logits/chosen: -2.3485
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4889        | 0.2899 | 40   | 0.4642          | 1.1544         | -0.1887          | 0.7944             | 1.3431          | -200.0950      | -188.7752    | -1.9876         | -2.0351       |
+| 0.3941        | 0.5797 | 80   | 0.4218          | -0.2275        | -2.2919          | 0.8044             | 2.0644          | -221.1273      | -202.5944    | -1.9449         | -1.9901       |
+| 0.3717        | 0.8696 | 120  | 0.4387          | -0.2101        | -2.4885          | 0.8286             | 2.2784          | -223.0936      | -202.4208    | -2.0902         | -2.1229       |
+| 0.1459        | 1.1594 | 160  | 0.4288          | -0.4029        | -3.3928          | 0.8286             | 2.9899          | -232.1363      | -204.3488    | -2.2733         | -2.3007       |
+| 0.1455        | 1.4493 | 200  | 0.4255          | -0.5338        | -3.6331          | 0.8165             | 3.0992          | -234.5387      | -205.6577    | -2.2466         | -2.2697       |
+| 0.1358        | 1.7391 | 240  | 0.4247          | -0.2714        | -3.6715          | 0.8327             | 3.4001          | -234.9227      | -203.0333    | -2.3605         | -2.3806       |
+| 0.0938        | 2.0290 | 280  | 0.4128          | -0.3136        | -3.7007          | 0.8266             | 3.3870          | -235.2147      | -203.4556    | -2.3725         | -2.3933       |
+| 0.0592        | 2.3188 | 320  | 0.4438          | -0.5767        | -4.1235          | 0.8165             | 3.5467          | -239.4429      | -206.0869    | -2.3109         | -2.3358       |
+| 0.0673        | 2.6087 | 360  | 0.4553          | -0.6264        | -4.3005          | 0.8206             | 3.6740          | -241.2126      | -206.5837    | -2.3254         | -2.3497       |
+| 0.0728        | 2.8986 | 400  | 0.4520          | -0.6855        | -4.3942          | 0.8185             | 3.7087          | -242.1503      | -207.1744    | -2.3247         | -2.3492       |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.3485426902770996,
+    "eval_logits/rejected": -2.32399582862854,
+    "eval_logps/chosen": -207.17623901367188,
+    "eval_logps/rejected": -242.1480255126953,
+    "eval_loss": 0.45268043875694275,
+    "eval_rewards/accuracies": 0.8165322542190552,
+    "eval_rewards/chosen": -0.6856781244277954,
+    "eval_rewards/margins": 3.7083182334899902,
+    "eval_rewards/rejected": -4.393996715545654,
+    "eval_runtime": 246.3688,
+    "eval_samples_per_second": 15.919,
+    "eval_steps_per_second": 0.252,
+    "total_flos": 4881795388538880.0,
+    "train_loss": 0.21833302825689316,
+    "train_runtime": 16364.2441,
+    "train_samples_per_second": 6.47,
+    "train_steps_per_second": 0.025
+}

checkpoint-120/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-120/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-120/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-120/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e40b873bd71b600c08220e434771c07090facd4443ba0c6b07e93f0af4be79
+size 4921618624

checkpoint-120/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c6699524f4655083b3649f18b14a5ae434f40f28991d2c4c25b21c4066893b
+size 4915917672

checkpoint-120/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84c6f427c02e2982e1462d89cea773d96ffd94d3ff71fc5f48c7ead78d72cb6
+size 4915917680

checkpoint-120/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563c89f0c94059695c61aea783f7a4610659f158fdb25e7db0e335105da16f50
+size 380134008

checkpoint-120/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-120/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-120/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-120/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-120/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-120/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8695652173913043,
+  "eval_steps": 40,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.036231884057971016,
+      "grad_norm": 61.66789827681496,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7321553230285645,
+      "logits/rejected": -2.7100937366485596,
+      "logps/chosen": -182.5845489501953,
+      "logps/rejected": -189.55001831054688,
+      "loss": 0.689,
+      "rewards/accuracies": 0.3187499940395355,
+      "rewards/chosen": -0.0021577859297394753,
+      "rewards/margins": 0.005646524019539356,
+      "rewards/rejected": -0.007804309483617544,
+      "step": 5
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 44.96703657621111,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.753889799118042,
+      "logits/rejected": -2.7519516944885254,
+      "logps/chosen": -197.34320068359375,
+      "logps/rejected": -184.00961303710938,
+      "loss": 0.6275,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.030874451622366905,
+      "rewards/margins": 0.18904080986976624,
+      "rewards/rejected": -0.15816636383533478,
+      "step": 10
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 51.54402636298773,
+      "learning_rate": 9.996221126793764e-07,
+      "logits/chosen": -2.694437265396118,
+      "logits/rejected": -2.691904067993164,
+      "logps/chosen": -203.14883422851562,
+      "logps/rejected": -204.52386474609375,
+      "loss": 0.5851,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.6205412745475769,
+      "rewards/margins": 0.9350436925888062,
+      "rewards/rejected": -0.314502477645874,
+      "step": 15
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 35.11282014809116,
+      "learning_rate": 9.984890219128145e-07,
+      "logits/chosen": -2.609405517578125,
+      "logits/rejected": -2.5795176029205322,
+      "logps/chosen": -188.33395385742188,
+      "logps/rejected": -192.52633666992188,
+      "loss": 0.5144,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.8838651776313782,
+      "rewards/margins": 1.275496244430542,
+      "rewards/rejected": -0.39163118600845337,
+      "step": 20
+    },
+    {
+      "epoch": 0.18115942028985507,
+      "grad_norm": 37.05591291167376,
+      "learning_rate": 9.966024404228493e-07,
+      "logits/chosen": -2.4429798126220703,
+      "logits/rejected": -2.4225034713745117,
+      "logps/chosen": -179.79977416992188,
+      "logps/rejected": -179.25279235839844,
+      "loss": 0.5036,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.40532931685447693,
+      "rewards/margins": 0.8947975039482117,
+      "rewards/rejected": -0.4894680976867676,
+      "step": 25
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 33.27618771325657,
+      "learning_rate": 9.939652198703783e-07,
+      "logits/chosen": -2.319044589996338,
+      "logits/rejected": -2.320253372192383,
+      "logps/chosen": -188.62039184570312,
+      "logps/rejected": -193.8806915283203,
+      "loss": 0.4987,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.6481167078018188,
+      "rewards/margins": 1.2183058261871338,
+      "rewards/rejected": -0.5701891183853149,
+      "step": 30
+    },
+    {
+      "epoch": 0.2536231884057971,
+      "grad_norm": 38.645073192304736,
+      "learning_rate": 9.905813465442354e-07,
+      "logits/chosen": -2.242053747177124,
+      "logits/rejected": -2.2155580520629883,
+      "logps/chosen": -203.94546508789062,
+      "logps/rejected": -194.8705291748047,
+      "loss": 0.5091,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.8871867060661316,
+      "rewards/margins": 1.2737131118774414,
+      "rewards/rejected": -0.3865264356136322,
+      "step": 35
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 30.937642063399068,
+      "learning_rate": 9.864559353357187e-07,
+      "logits/chosen": -2.0998620986938477,
+      "logits/rejected": -2.094836473464966,
+      "logps/chosen": -182.6898956298828,
+      "logps/rejected": -185.73983764648438,
+      "loss": 0.4889,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.0410809516906738,
+      "rewards/margins": 1.0222995281219482,
+      "rewards/rejected": 0.018781563267111778,
+      "step": 40
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "eval_logits/chosen": -2.035081624984741,
+      "eval_logits/rejected": -1.9875677824020386,
+      "eval_logps/chosen": -188.77523803710938,
+      "eval_logps/rejected": -200.09498596191406,
+      "eval_loss": 0.4642000198364258,
+      "eval_rewards/accuracies": 0.7943548560142517,
+      "eval_rewards/chosen": 1.1544201374053955,
+      "eval_rewards/margins": 1.3431099653244019,
+      "eval_rewards/rejected": -0.18868987262248993,
+      "eval_runtime": 248.6586,
+      "eval_samples_per_second": 15.773,
+      "eval_steps_per_second": 0.249,
+      "step": 40
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 29.205255063362404,
+      "learning_rate": 9.815952220071804e-07,
+      "logits/chosen": -1.9733244180679321,
+      "logits/rejected": -1.9242098331451416,
+      "logps/chosen": -195.65652465820312,
+      "logps/rejected": -221.744384765625,
+      "loss": 0.4587,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.3803393840789795,
+      "rewards/margins": 1.8610279560089111,
+      "rewards/rejected": -0.4806883931159973,
+      "step": 45
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 29.678687938529745,
+      "learning_rate": 9.76006553766365e-07,
+      "logits/chosen": -1.8085625171661377,
+      "logits/rejected": -1.772071123123169,
+      "logps/chosen": -198.9405517578125,
+      "logps/rejected": -203.29978942871094,
+      "loss": 0.4531,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 0.8211376070976257,
+      "rewards/margins": 1.646414041519165,
+      "rewards/rejected": -0.8252763748168945,
+      "step": 50
+    },
+    {
+      "epoch": 0.39855072463768115,
+      "grad_norm": 30.73732601293307,
+      "learning_rate": 9.696983781607415e-07,
+      "logits/chosen": -1.7908868789672852,
+      "logits/rejected": -1.7599233388900757,
+      "logps/chosen": -183.01809692382812,
+      "logps/rejected": -172.02801513671875,
+      "loss": 0.4595,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.607209324836731,
+      "rewards/margins": 1.649515151977539,
+      "rewards/rejected": -1.042305827140808,
+      "step": 55
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 41.49881496846909,
+      "learning_rate": 9.626802303086209e-07,
+      "logits/chosen": -1.9050066471099854,
+      "logits/rejected": -1.8625679016113281,
+      "logps/chosen": -186.8179931640625,
+      "logps/rejected": -194.26707458496094,
+      "loss": 0.4276,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.4140642285346985,
+      "rewards/margins": 1.712418794631958,
+      "rewards/rejected": -1.2983543872833252,
+      "step": 60
+    },
+    {
+      "epoch": 0.47101449275362317,
+      "grad_norm": 36.480881476794956,
+      "learning_rate": 9.549627184863528e-07,
+      "logits/chosen": -2.1638290882110596,
+      "logits/rejected": -2.0793471336364746,
+      "logps/chosen": -191.9010467529297,
+      "logps/rejected": -193.20651245117188,
+      "loss": 0.4293,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.045776158571243286,
+      "rewards/margins": 1.6033704280853271,
+      "rewards/rejected": -1.5575940608978271,
+      "step": 65
+    },
+    {
+      "epoch": 0.5072463768115942,
+      "grad_norm": 26.318712537847357,
+      "learning_rate": 9.465575080933957e-07,
+      "logits/chosen": -2.1214632987976074,
+      "logits/rejected": -2.081162214279175,
+      "logps/chosen": -172.66419982910156,
+      "logps/rejected": -208.19149780273438,
+      "loss": 0.3963,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.17696644365787506,
+      "rewards/margins": 1.8183233737945557,
+      "rewards/rejected": -1.6413570642471313,
+      "step": 70
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 32.35315227999789,
+      "learning_rate": 9.374773040194878e-07,
+      "logits/chosen": -2.1271562576293945,
+      "logits/rejected": -2.0680038928985596,
+      "logps/chosen": -205.5594482421875,
+      "logps/rejected": -210.7834014892578,
+      "loss": 0.4353,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.16769471764564514,
+      "rewards/margins": 1.786273717880249,
+      "rewards/rejected": -1.6185792684555054,
+      "step": 75
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 29.96593011887677,
+      "learning_rate": 9.277358314405818e-07,
+      "logits/chosen": -2.046504497528076,
+      "logits/rejected": -2.0122628211975098,
+      "logps/chosen": -189.37771606445312,
+      "logps/rejected": -206.10659790039062,
+      "loss": 0.3941,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2374907284975052,
+      "rewards/margins": 1.910300612449646,
+      "rewards/rejected": -2.1477913856506348,
+      "step": 80
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "eval_logits/chosen": -1.9900643825531006,
+      "eval_logits/rejected": -1.9449083805084229,
+      "eval_logps/chosen": -202.59437561035156,
+      "eval_logps/rejected": -221.12725830078125,
+      "eval_loss": 0.4217630624771118,
+      "eval_rewards/accuracies": 0.8044354915618896,
+      "eval_rewards/chosen": -0.22749020159244537,
+      "eval_rewards/margins": 2.0644266605377197,
+      "eval_rewards/rejected": -2.291916847229004,
+      "eval_runtime": 247.3121,
+      "eval_samples_per_second": 15.859,
+      "eval_steps_per_second": 0.251,
+      "step": 80
+    },
+    {
+      "epoch": 0.6159420289855072,
+      "grad_norm": 34.207898226903815,
+      "learning_rate": 9.173478150725651e-07,
+      "logits/chosen": -2.0169568061828613,
+      "logits/rejected": -1.9391515254974365,
+      "logps/chosen": -209.73440551757812,
+      "logps/rejected": -215.14205932617188,
+      "loss": 0.422,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.1130056157708168,
+      "rewards/margins": 2.3998470306396484,
+      "rewards/rejected": -2.2868411540985107,
+      "step": 85
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 28.850805260840193,
+      "learning_rate": 9.063289569141251e-07,
+      "logits/chosen": -2.1180360317230225,
+      "logits/rejected": -2.080235242843628,
+      "logps/chosen": -214.2292022705078,
+      "logps/rejected": -223.37564086914062,
+      "loss": 0.4135,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.5250645279884338,
+      "rewards/margins": 2.2779579162597656,
+      "rewards/rejected": -1.7528936862945557,
+      "step": 90
+    },
+    {
+      "epoch": 0.6884057971014492,
+      "grad_norm": 34.73111091101309,
+      "learning_rate": 8.946959125124051e-07,
+      "logits/chosen": -2.2047152519226074,
+      "logits/rejected": -2.1581788063049316,
+      "logps/chosen": -209.3234405517578,
+      "logps/rejected": -195.6946563720703,
+      "loss": 0.4077,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.25443512201309204,
+      "rewards/margins": 2.2029635906219482,
+      "rewards/rejected": -1.948528528213501,
+      "step": 95
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 32.202226649445414,
+      "learning_rate": 8.824662657873238e-07,
+      "logits/chosen": -2.256134510040283,
+      "logits/rejected": -2.2395310401916504,
+      "logps/chosen": -176.19464111328125,
+      "logps/rejected": -209.0999298095703,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3457742929458618,
+      "rewards/margins": 1.9383150339126587,
+      "rewards/rejected": -2.2840893268585205,
+      "step": 100
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 31.35693490170537,
+      "learning_rate": 8.696585024526135e-07,
+      "logits/chosen": -2.3358142375946045,
+      "logits/rejected": -2.307068347930908,
+      "logps/chosen": -191.8298797607422,
+      "logps/rejected": -227.55612182617188,
+      "loss": 0.4017,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2825666069984436,
+      "rewards/margins": 2.5402400493621826,
+      "rewards/rejected": -2.8228065967559814,
+      "step": 105
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 36.29919961993296,
+      "learning_rate": 8.562919820737535e-07,
+      "logits/chosen": -2.2931602001190186,
+      "logits/rejected": -2.2568557262420654,
+      "logps/chosen": -207.34158325195312,
+      "logps/rejected": -208.9143524169922,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.3017815351486206,
+      "rewards/margins": 2.3830084800720215,
+      "rewards/rejected": -2.6847901344299316,
+      "step": 110
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 28.819478551304137,
+      "learning_rate": 8.423869088050315e-07,
+      "logits/chosen": -2.2734763622283936,
+      "logits/rejected": -2.2522785663604736,
+      "logps/chosen": -195.6924591064453,
+      "logps/rejected": -221.85104370117188,
+      "loss": 0.3892,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.12773282825946808,
+      "rewards/margins": 2.3888843059539795,
+      "rewards/rejected": -2.5166170597076416,
+      "step": 115
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 37.085951928654964,
+      "learning_rate": 8.2796430084997e-07,
+      "logits/chosen": -2.2070839405059814,
+      "logits/rejected": -2.1736464500427246,
+      "logps/chosen": -196.70889282226562,
+      "logps/rejected": -207.93417358398438,
+      "loss": 0.3717,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.12862932682037354,
+      "rewards/margins": 2.698848009109497,
+      "rewards/rejected": -2.570218563079834,
+      "step": 120
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_logits/chosen": -2.122933864593506,
+      "eval_logits/rejected": -2.0901710987091064,
+      "eval_logps/chosen": -202.4208221435547,
+      "eval_logps/rejected": -223.09356689453125,
+      "eval_loss": 0.438678115606308,
+      "eval_rewards/accuracies": 0.8286290168762207,
+      "eval_rewards/chosen": -0.2101391851902008,
+      "eval_rewards/margins": 2.278407573699951,
+      "eval_rewards/rejected": -2.488546848297119,
+      "eval_runtime": 247.3754,
+      "eval_samples_per_second": 15.854,
+      "eval_steps_per_second": 0.251,
+      "step": 120
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1414680891359232.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af79ff24bae38840a3c8efe3d28d0cc2a77ca640996f1dd8521f5747a2625682
+size 7096

checkpoint-160/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-160/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-160/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-160/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5da867f9d0130e643755f51786e2ee6be28ec716a4ec5d51bb5966d53d3119
+size 4921618624

checkpoint-160/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c64f563545c1d629bc913dfbf65b32ead3f13fd8037b23a4c12f305a383ab1
+size 4915917672

checkpoint-160/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ddddabd722f7f44910af6d7a8e33882b6237d9f98759b20d8486434a8fb10f
+size 4915917680

checkpoint-160/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1221e691075d89324fd24160979b901e8c5d17d09554a049568326b3370a5920
+size 380134008

checkpoint-160/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-160/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-160/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-160/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-160/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-160/trainer_state.json

@@ -0,0 +1,577 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1594202898550725,
+  "eval_steps": 40,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.036231884057971016,
+      "grad_norm": 61.66789827681496,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7321553230285645,
+      "logits/rejected": -2.7100937366485596,
+      "logps/chosen": -182.5845489501953,
+      "logps/rejected": -189.55001831054688,
+      "loss": 0.689,
+      "rewards/accuracies": 0.3187499940395355,
+      "rewards/chosen": -0.0021577859297394753,
+      "rewards/margins": 0.005646524019539356,
+      "rewards/rejected": -0.007804309483617544,
+      "step": 5
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 44.96703657621111,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.753889799118042,
+      "logits/rejected": -2.7519516944885254,
+      "logps/chosen": -197.34320068359375,
+      "logps/rejected": -184.00961303710938,
+      "loss": 0.6275,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.030874451622366905,
+      "rewards/margins": 0.18904080986976624,
+      "rewards/rejected": -0.15816636383533478,
+      "step": 10
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 51.54402636298773,
+      "learning_rate": 9.996221126793764e-07,
+      "logits/chosen": -2.694437265396118,
+      "logits/rejected": -2.691904067993164,
+      "logps/chosen": -203.14883422851562,
+      "logps/rejected": -204.52386474609375,
+      "loss": 0.5851,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.6205412745475769,
+      "rewards/margins": 0.9350436925888062,
+      "rewards/rejected": -0.314502477645874,
+      "step": 15
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 35.11282014809116,
+      "learning_rate": 9.984890219128145e-07,
+      "logits/chosen": -2.609405517578125,
+      "logits/rejected": -2.5795176029205322,
+      "logps/chosen": -188.33395385742188,
+      "logps/rejected": -192.52633666992188,
+      "loss": 0.5144,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.8838651776313782,
+      "rewards/margins": 1.275496244430542,
+      "rewards/rejected": -0.39163118600845337,
+      "step": 20
+    },
+    {
+      "epoch": 0.18115942028985507,
+      "grad_norm": 37.05591291167376,
+      "learning_rate": 9.966024404228493e-07,
+      "logits/chosen": -2.4429798126220703,
+      "logits/rejected": -2.4225034713745117,
+      "logps/chosen": -179.79977416992188,
+      "logps/rejected": -179.25279235839844,
+      "loss": 0.5036,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.40532931685447693,
+      "rewards/margins": 0.8947975039482117,
+      "rewards/rejected": -0.4894680976867676,
+      "step": 25
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 33.27618771325657,
+      "learning_rate": 9.939652198703783e-07,
+      "logits/chosen": -2.319044589996338,
+      "logits/rejected": -2.320253372192383,
+      "logps/chosen": -188.62039184570312,
+      "logps/rejected": -193.8806915283203,
+      "loss": 0.4987,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.6481167078018188,
+      "rewards/margins": 1.2183058261871338,
+      "rewards/rejected": -0.5701891183853149,
+      "step": 30
+    },
+    {
+      "epoch": 0.2536231884057971,
+      "grad_norm": 38.645073192304736,
+      "learning_rate": 9.905813465442354e-07,
+      "logits/chosen": -2.242053747177124,
+      "logits/rejected": -2.2155580520629883,
+      "logps/chosen": -203.94546508789062,
+      "logps/rejected": -194.8705291748047,
+      "loss": 0.5091,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.8871867060661316,
+      "rewards/margins": 1.2737131118774414,
+      "rewards/rejected": -0.3865264356136322,
+      "step": 35
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 30.937642063399068,
+      "learning_rate": 9.864559353357187e-07,
+      "logits/chosen": -2.0998620986938477,
+      "logits/rejected": -2.094836473464966,
+      "logps/chosen": -182.6898956298828,
+      "logps/rejected": -185.73983764648438,
+      "loss": 0.4889,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.0410809516906738,
+      "rewards/margins": 1.0222995281219482,
+      "rewards/rejected": 0.018781563267111778,
+      "step": 40
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "eval_logits/chosen": -2.035081624984741,
+      "eval_logits/rejected": -1.9875677824020386,
+      "eval_logps/chosen": -188.77523803710938,
+      "eval_logps/rejected": -200.09498596191406,
+      "eval_loss": 0.4642000198364258,
+      "eval_rewards/accuracies": 0.7943548560142517,
+      "eval_rewards/chosen": 1.1544201374053955,
+      "eval_rewards/margins": 1.3431099653244019,
+      "eval_rewards/rejected": -0.18868987262248993,
+      "eval_runtime": 248.6586,
+      "eval_samples_per_second": 15.773,
+      "eval_steps_per_second": 0.249,
+      "step": 40
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 29.205255063362404,
+      "learning_rate": 9.815952220071804e-07,
+      "logits/chosen": -1.9733244180679321,
+      "logits/rejected": -1.9242098331451416,
+      "logps/chosen": -195.65652465820312,
+      "logps/rejected": -221.744384765625,
+      "loss": 0.4587,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.3803393840789795,
+      "rewards/margins": 1.8610279560089111,
+      "rewards/rejected": -0.4806883931159973,
+      "step": 45
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 29.678687938529745,
+      "learning_rate": 9.76006553766365e-07,
+      "logits/chosen": -1.8085625171661377,
+      "logits/rejected": -1.772071123123169,
+      "logps/chosen": -198.9405517578125,
+      "logps/rejected": -203.29978942871094,
+      "loss": 0.4531,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 0.8211376070976257,
+      "rewards/margins": 1.646414041519165,
+      "rewards/rejected": -0.8252763748168945,
+      "step": 50
+    },
+    {
+      "epoch": 0.39855072463768115,
+      "grad_norm": 30.73732601293307,
+      "learning_rate": 9.696983781607415e-07,
+      "logits/chosen": -1.7908868789672852,
+      "logits/rejected": -1.7599233388900757,
+      "logps/chosen": -183.01809692382812,
+      "logps/rejected": -172.02801513671875,
+      "loss": 0.4595,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.607209324836731,
+      "rewards/margins": 1.649515151977539,
+      "rewards/rejected": -1.042305827140808,
+      "step": 55
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 41.49881496846909,
+      "learning_rate": 9.626802303086209e-07,
+      "logits/chosen": -1.9050066471099854,
+      "logits/rejected": -1.8625679016113281,
+      "logps/chosen": -186.8179931640625,
+      "logps/rejected": -194.26707458496094,
+      "loss": 0.4276,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.4140642285346985,
+      "rewards/margins": 1.712418794631958,
+      "rewards/rejected": -1.2983543872833252,
+      "step": 60
+    },
+    {
+      "epoch": 0.47101449275362317,
+      "grad_norm": 36.480881476794956,
+      "learning_rate": 9.549627184863528e-07,
+      "logits/chosen": -2.1638290882110596,
+      "logits/rejected": -2.0793471336364746,
+      "logps/chosen": -191.9010467529297,
+      "logps/rejected": -193.20651245117188,
+      "loss": 0.4293,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.045776158571243286,
+      "rewards/margins": 1.6033704280853271,
+      "rewards/rejected": -1.5575940608978271,
+      "step": 65
+    },
+    {
+      "epoch": 0.5072463768115942,
+      "grad_norm": 26.318712537847357,
+      "learning_rate": 9.465575080933957e-07,
+      "logits/chosen": -2.1214632987976074,
+      "logits/rejected": -2.081162214279175,
+      "logps/chosen": -172.66419982910156,
+      "logps/rejected": -208.19149780273438,
+      "loss": 0.3963,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.17696644365787506,
+      "rewards/margins": 1.8183233737945557,
+      "rewards/rejected": -1.6413570642471313,
+      "step": 70
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 32.35315227999789,
+      "learning_rate": 9.374773040194878e-07,
+      "logits/chosen": -2.1271562576293945,
+      "logits/rejected": -2.0680038928985596,
+      "logps/chosen": -205.5594482421875,
+      "logps/rejected": -210.7834014892578,
+      "loss": 0.4353,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.16769471764564514,
+      "rewards/margins": 1.786273717880249,
+      "rewards/rejected": -1.6185792684555054,
+      "step": 75
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 29.96593011887677,
+      "learning_rate": 9.277358314405818e-07,
+      "logits/chosen": -2.046504497528076,
+      "logits/rejected": -2.0122628211975098,
+      "logps/chosen": -189.37771606445312,
+      "logps/rejected": -206.10659790039062,
+      "loss": 0.3941,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2374907284975052,
+      "rewards/margins": 1.910300612449646,
+      "rewards/rejected": -2.1477913856506348,
+      "step": 80
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "eval_logits/chosen": -1.9900643825531006,
+      "eval_logits/rejected": -1.9449083805084229,
+      "eval_logps/chosen": -202.59437561035156,
+      "eval_logps/rejected": -221.12725830078125,
+      "eval_loss": 0.4217630624771118,
+      "eval_rewards/accuracies": 0.8044354915618896,
+      "eval_rewards/chosen": -0.22749020159244537,
+      "eval_rewards/margins": 2.0644266605377197,
+      "eval_rewards/rejected": -2.291916847229004,
+      "eval_runtime": 247.3121,
+      "eval_samples_per_second": 15.859,
+      "eval_steps_per_second": 0.251,
+      "step": 80
+    },
+    {
+      "epoch": 0.6159420289855072,
+      "grad_norm": 34.207898226903815,
+      "learning_rate": 9.173478150725651e-07,
+      "logits/chosen": -2.0169568061828613,
+      "logits/rejected": -1.9391515254974365,
+      "logps/chosen": -209.73440551757812,
+      "logps/rejected": -215.14205932617188,
+      "loss": 0.422,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.1130056157708168,
+      "rewards/margins": 2.3998470306396484,
+      "rewards/rejected": -2.2868411540985107,
+      "step": 85
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 28.850805260840193,
+      "learning_rate": 9.063289569141251e-07,
+      "logits/chosen": -2.1180360317230225,
+      "logits/rejected": -2.080235242843628,
+      "logps/chosen": -214.2292022705078,
+      "logps/rejected": -223.37564086914062,
+      "loss": 0.4135,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.5250645279884338,
+      "rewards/margins": 2.2779579162597656,
+      "rewards/rejected": -1.7528936862945557,
+      "step": 90
+    },
+    {
+      "epoch": 0.6884057971014492,
+      "grad_norm": 34.73111091101309,
+      "learning_rate": 8.946959125124051e-07,
+      "logits/chosen": -2.2047152519226074,
+      "logits/rejected": -2.1581788063049316,
+      "logps/chosen": -209.3234405517578,
+      "logps/rejected": -195.6946563720703,
+      "loss": 0.4077,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.25443512201309204,
+      "rewards/margins": 2.2029635906219482,
+      "rewards/rejected": -1.948528528213501,
+      "step": 95
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 32.202226649445414,
+      "learning_rate": 8.824662657873238e-07,
+      "logits/chosen": -2.256134510040283,
+      "logits/rejected": -2.2395310401916504,
+      "logps/chosen": -176.19464111328125,
+      "logps/rejected": -209.0999298095703,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3457742929458618,
+      "rewards/margins": 1.9383150339126587,
+      "rewards/rejected": -2.2840893268585205,
+      "step": 100
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 31.35693490170537,
+      "learning_rate": 8.696585024526135e-07,
+      "logits/chosen": -2.3358142375946045,
+      "logits/rejected": -2.307068347930908,
+      "logps/chosen": -191.8298797607422,
+      "logps/rejected": -227.55612182617188,
+      "loss": 0.4017,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2825666069984436,
+      "rewards/margins": 2.5402400493621826,
+      "rewards/rejected": -2.8228065967559814,
+      "step": 105
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 36.29919961993296,
+      "learning_rate": 8.562919820737535e-07,
+      "logits/chosen": -2.2931602001190186,
+      "logits/rejected": -2.2568557262420654,
+      "logps/chosen": -207.34158325195312,
+      "logps/rejected": -208.9143524169922,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.3017815351486206,
+      "rewards/margins": 2.3830084800720215,
+      "rewards/rejected": -2.6847901344299316,
+      "step": 110
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 28.819478551304137,
+      "learning_rate": 8.423869088050315e-07,
+      "logits/chosen": -2.2734763622283936,
+      "logits/rejected": -2.2522785663604736,
+      "logps/chosen": -195.6924591064453,
+      "logps/rejected": -221.85104370117188,
+      "loss": 0.3892,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.12773282825946808,
+      "rewards/margins": 2.3888843059539795,
+      "rewards/rejected": -2.5166170597076416,
+      "step": 115
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 37.085951928654964,
+      "learning_rate": 8.2796430084997e-07,
+      "logits/chosen": -2.2070839405059814,
+      "logits/rejected": -2.1736464500427246,
+      "logps/chosen": -196.70889282226562,
+      "logps/rejected": -207.93417358398438,
+      "loss": 0.3717,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.12862932682037354,
+      "rewards/margins": 2.698848009109497,
+      "rewards/rejected": -2.570218563079834,
+      "step": 120
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_logits/chosen": -2.122933864593506,
+      "eval_logits/rejected": -2.0901710987091064,
+      "eval_logps/chosen": -202.4208221435547,
+      "eval_logps/rejected": -223.09356689453125,
+      "eval_loss": 0.438678115606308,
+      "eval_rewards/accuracies": 0.8286290168762207,
+      "eval_rewards/chosen": -0.2101391851902008,
+      "eval_rewards/margins": 2.278407573699951,
+      "eval_rewards/rejected": -2.488546848297119,
+      "eval_runtime": 247.3754,
+      "eval_samples_per_second": 15.854,
+      "eval_steps_per_second": 0.251,
+      "step": 120
+    },
+    {
+      "epoch": 0.9057971014492754,
+      "grad_norm": 27.843666767086823,
+      "learning_rate": 8.130459586912753e-07,
+      "logits/chosen": -2.0930094718933105,
+      "logits/rejected": -2.0791330337524414,
+      "logps/chosen": -220.4320526123047,
+      "logps/rejected": -218.3594512939453,
+      "loss": 0.4575,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.9592973589897156,
+      "rewards/margins": 1.66092050075531,
+      "rewards/rejected": -2.620218276977539,
+      "step": 125
+    },
+    {
+      "epoch": 0.9420289855072463,
+      "grad_norm": 28.902451958691426,
+      "learning_rate": 7.97654432138333e-07,
+      "logits/chosen": -2.1393418312072754,
+      "logits/rejected": -2.103482723236084,
+      "logps/chosen": -214.5059051513672,
+      "logps/rejected": -248.8673858642578,
+      "loss": 0.388,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.1911260336637497,
+      "rewards/margins": 2.8205361366271973,
+      "rewards/rejected": -3.011662006378174,
+      "step": 130
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 26.45174989804514,
+      "learning_rate": 7.81812986242061e-07,
+      "logits/chosen": -2.2018837928771973,
+      "logits/rejected": -2.1459240913391113,
+      "logps/chosen": -193.5723419189453,
+      "logps/rejected": -233.81838989257812,
+      "loss": 0.365,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.10008885711431503,
+      "rewards/margins": 3.072911262512207,
+      "rewards/rejected": -2.972822427749634,
+      "step": 135
+    },
+    {
+      "epoch": 1.0144927536231885,
+      "grad_norm": 16.755101670108846,
+      "learning_rate": 7.655455661286375e-07,
+      "logits/chosen": -2.190566301345825,
+      "logits/rejected": -2.1852922439575195,
+      "logps/chosen": -190.56027221679688,
+      "logps/rejected": -234.6202392578125,
+      "loss": 0.2524,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 0.05487387627363205,
+      "rewards/margins": 3.58606219291687,
+      "rewards/rejected": -3.531188488006592,
+      "step": 140
+    },
+    {
+      "epoch": 1.0507246376811594,
+      "grad_norm": 16.022443175608785,
+      "learning_rate": 7.488767608052628e-07,
+      "logits/chosen": -2.2735958099365234,
+      "logits/rejected": -2.199552059173584,
+      "logps/chosen": -190.21511840820312,
+      "logps/rejected": -237.59854125976562,
+      "loss": 0.171,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.7184330821037292,
+      "rewards/margins": 4.115548133850098,
+      "rewards/rejected": -3.3971149921417236,
+      "step": 145
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 16.37925141930124,
+      "learning_rate": 7.318317659926636e-07,
+      "logits/chosen": -2.250054121017456,
+      "logits/rejected": -2.221043109893799,
+      "logps/chosen": -174.0218048095703,
+      "logps/rejected": -237.14120483398438,
+      "loss": 0.1436,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.0139648914337158,
+      "rewards/margins": 4.169236660003662,
+      "rewards/rejected": -3.1552722454071045,
+      "step": 150
+    },
+    {
+      "epoch": 1.1231884057971016,
+      "grad_norm": 13.693805739113818,
+      "learning_rate": 7.144363460405189e-07,
+      "logits/chosen": -2.3314082622528076,
+      "logits/rejected": -2.2712883949279785,
+      "logps/chosen": -192.2017059326172,
+      "logps/rejected": -236.91586303710938,
+      "loss": 0.1415,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.1952037811279297,
+      "rewards/margins": 4.705626487731934,
+      "rewards/rejected": -3.510422945022583,
+      "step": 155
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 13.203700040695288,
+      "learning_rate": 6.967167949833762e-07,
+      "logits/chosen": -2.324735164642334,
+      "logits/rejected": -2.283231258392334,
+      "logps/chosen": -194.0807342529297,
+      "logps/rejected": -247.2218475341797,
+      "loss": 0.1459,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.3761358857154846,
+      "rewards/margins": 4.9711785316467285,
+      "rewards/rejected": -4.595042705535889,
+      "step": 160
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "eval_logits/chosen": -2.3007450103759766,
+      "eval_logits/rejected": -2.273284673690796,
+      "eval_logps/chosen": -204.34878540039062,
+      "eval_logps/rejected": -232.13629150390625,
+      "eval_loss": 0.42876046895980835,
+      "eval_rewards/accuracies": 0.8286290168762207,
+      "eval_rewards/chosen": -0.40293240547180176,
+      "eval_rewards/margins": 2.9898877143859863,
+      "eval_rewards/rejected": -3.392819881439209,
+      "eval_runtime": 247.3207,
+      "eval_samples_per_second": 15.858,
+      "eval_steps_per_second": 0.251,
+      "step": 160
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1886397149478912.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af79ff24bae38840a3c8efe3d28d0cc2a77ca640996f1dd8521f5747a2625682
+size 7096

checkpoint-200/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-200/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

checkpoint-200/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

checkpoint-200/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537a3da88cf529a9efeb07b422fd7bdac0d807d05846dc56c25b76d92af41cbf
+size 4921618624

checkpoint-200/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d006fef53cce2f2e43034cb2db577d07562d64646856b232f7e753dc0814fd4d
+size 4915917672

checkpoint-200/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c639af878f3974616a77f6a988beb204d98f25d90fb2b3b7c0bf37f9bc1980
+size 4915917680

checkpoint-200/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3b51d06805ebb8ccae561ddb4f54919d8269efc2a5a65af5addedb31e5778b
+size 380134008

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,694 @@
+{
+  "metadata": {
+    "total_size": 15133495296
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00004.safetensors",
+    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-200/preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4492753623188406,
+  "eval_steps": 40,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.036231884057971016,
+      "grad_norm": 61.66789827681496,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.7321553230285645,
+      "logits/rejected": -2.7100937366485596,
+      "logps/chosen": -182.5845489501953,
+      "logps/rejected": -189.55001831054688,
+      "loss": 0.689,
+      "rewards/accuracies": 0.3187499940395355,
+      "rewards/chosen": -0.0021577859297394753,
+      "rewards/margins": 0.005646524019539356,
+      "rewards/rejected": -0.007804309483617544,
+      "step": 5
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 44.96703657621111,
+      "learning_rate": 1e-06,
+      "logits/chosen": -2.753889799118042,
+      "logits/rejected": -2.7519516944885254,
+      "logps/chosen": -197.34320068359375,
+      "logps/rejected": -184.00961303710938,
+      "loss": 0.6275,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.030874451622366905,
+      "rewards/margins": 0.18904080986976624,
+      "rewards/rejected": -0.15816636383533478,
+      "step": 10
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 51.54402636298773,
+      "learning_rate": 9.996221126793764e-07,
+      "logits/chosen": -2.694437265396118,
+      "logits/rejected": -2.691904067993164,
+      "logps/chosen": -203.14883422851562,
+      "logps/rejected": -204.52386474609375,
+      "loss": 0.5851,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.6205412745475769,
+      "rewards/margins": 0.9350436925888062,
+      "rewards/rejected": -0.314502477645874,
+      "step": 15
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 35.11282014809116,
+      "learning_rate": 9.984890219128145e-07,
+      "logits/chosen": -2.609405517578125,
+      "logits/rejected": -2.5795176029205322,
+      "logps/chosen": -188.33395385742188,
+      "logps/rejected": -192.52633666992188,
+      "loss": 0.5144,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.8838651776313782,
+      "rewards/margins": 1.275496244430542,
+      "rewards/rejected": -0.39163118600845337,
+      "step": 20
+    },
+    {
+      "epoch": 0.18115942028985507,
+      "grad_norm": 37.05591291167376,
+      "learning_rate": 9.966024404228493e-07,
+      "logits/chosen": -2.4429798126220703,
+      "logits/rejected": -2.4225034713745117,
+      "logps/chosen": -179.79977416992188,
+      "logps/rejected": -179.25279235839844,
+      "loss": 0.5036,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.40532931685447693,
+      "rewards/margins": 0.8947975039482117,
+      "rewards/rejected": -0.4894680976867676,
+      "step": 25
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 33.27618771325657,
+      "learning_rate": 9.939652198703783e-07,
+      "logits/chosen": -2.319044589996338,
+      "logits/rejected": -2.320253372192383,
+      "logps/chosen": -188.62039184570312,
+      "logps/rejected": -193.8806915283203,
+      "loss": 0.4987,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.6481167078018188,
+      "rewards/margins": 1.2183058261871338,
+      "rewards/rejected": -0.5701891183853149,
+      "step": 30
+    },
+    {
+      "epoch": 0.2536231884057971,
+      "grad_norm": 38.645073192304736,
+      "learning_rate": 9.905813465442354e-07,
+      "logits/chosen": -2.242053747177124,
+      "logits/rejected": -2.2155580520629883,
+      "logps/chosen": -203.94546508789062,
+      "logps/rejected": -194.8705291748047,
+      "loss": 0.5091,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.8871867060661316,
+      "rewards/margins": 1.2737131118774414,
+      "rewards/rejected": -0.3865264356136322,
+      "step": 35
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 30.937642063399068,
+      "learning_rate": 9.864559353357187e-07,
+      "logits/chosen": -2.0998620986938477,
+      "logits/rejected": -2.094836473464966,
+      "logps/chosen": -182.6898956298828,
+      "logps/rejected": -185.73983764648438,
+      "loss": 0.4889,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.0410809516906738,
+      "rewards/margins": 1.0222995281219482,
+      "rewards/rejected": 0.018781563267111778,
+      "step": 40
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "eval_logits/chosen": -2.035081624984741,
+      "eval_logits/rejected": -1.9875677824020386,
+      "eval_logps/chosen": -188.77523803710938,
+      "eval_logps/rejected": -200.09498596191406,
+      "eval_loss": 0.4642000198364258,
+      "eval_rewards/accuracies": 0.7943548560142517,
+      "eval_rewards/chosen": 1.1544201374053955,
+      "eval_rewards/margins": 1.3431099653244019,
+      "eval_rewards/rejected": -0.18868987262248993,
+      "eval_runtime": 248.6586,
+      "eval_samples_per_second": 15.773,
+      "eval_steps_per_second": 0.249,
+      "step": 40
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 29.205255063362404,
+      "learning_rate": 9.815952220071804e-07,
+      "logits/chosen": -1.9733244180679321,
+      "logits/rejected": -1.9242098331451416,
+      "logps/chosen": -195.65652465820312,
+      "logps/rejected": -221.744384765625,
+      "loss": 0.4587,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.3803393840789795,
+      "rewards/margins": 1.8610279560089111,
+      "rewards/rejected": -0.4806883931159973,
+      "step": 45
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 29.678687938529745,
+      "learning_rate": 9.76006553766365e-07,
+      "logits/chosen": -1.8085625171661377,
+      "logits/rejected": -1.772071123123169,
+      "logps/chosen": -198.9405517578125,
+      "logps/rejected": -203.29978942871094,
+      "loss": 0.4531,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": 0.8211376070976257,
+      "rewards/margins": 1.646414041519165,
+      "rewards/rejected": -0.8252763748168945,
+      "step": 50
+    },
+    {
+      "epoch": 0.39855072463768115,
+      "grad_norm": 30.73732601293307,
+      "learning_rate": 9.696983781607415e-07,
+      "logits/chosen": -1.7908868789672852,
+      "logits/rejected": -1.7599233388900757,
+      "logps/chosen": -183.01809692382812,
+      "logps/rejected": -172.02801513671875,
+      "loss": 0.4595,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.607209324836731,
+      "rewards/margins": 1.649515151977539,
+      "rewards/rejected": -1.042305827140808,
+      "step": 55
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 41.49881496846909,
+      "learning_rate": 9.626802303086209e-07,
+      "logits/chosen": -1.9050066471099854,
+      "logits/rejected": -1.8625679016113281,
+      "logps/chosen": -186.8179931640625,
+      "logps/rejected": -194.26707458496094,
+      "loss": 0.4276,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.4140642285346985,
+      "rewards/margins": 1.712418794631958,
+      "rewards/rejected": -1.2983543872833252,
+      "step": 60
+    },
+    {
+      "epoch": 0.47101449275362317,
+      "grad_norm": 36.480881476794956,
+      "learning_rate": 9.549627184863528e-07,
+      "logits/chosen": -2.1638290882110596,
+      "logits/rejected": -2.0793471336364746,
+      "logps/chosen": -191.9010467529297,
+      "logps/rejected": -193.20651245117188,
+      "loss": 0.4293,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.045776158571243286,
+      "rewards/margins": 1.6033704280853271,
+      "rewards/rejected": -1.5575940608978271,
+      "step": 65
+    },
+    {
+      "epoch": 0.5072463768115942,
+      "grad_norm": 26.318712537847357,
+      "learning_rate": 9.465575080933957e-07,
+      "logits/chosen": -2.1214632987976074,
+      "logits/rejected": -2.081162214279175,
+      "logps/chosen": -172.66419982910156,
+      "logps/rejected": -208.19149780273438,
+      "loss": 0.3963,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.17696644365787506,
+      "rewards/margins": 1.8183233737945557,
+      "rewards/rejected": -1.6413570642471313,
+      "step": 70
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 32.35315227999789,
+      "learning_rate": 9.374773040194878e-07,
+      "logits/chosen": -2.1271562576293945,
+      "logits/rejected": -2.0680038928985596,
+      "logps/chosen": -205.5594482421875,
+      "logps/rejected": -210.7834014892578,
+      "loss": 0.4353,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.16769471764564514,
+      "rewards/margins": 1.786273717880249,
+      "rewards/rejected": -1.6185792684555054,
+      "step": 75
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 29.96593011887677,
+      "learning_rate": 9.277358314405818e-07,
+      "logits/chosen": -2.046504497528076,
+      "logits/rejected": -2.0122628211975098,
+      "logps/chosen": -189.37771606445312,
+      "logps/rejected": -206.10659790039062,
+      "loss": 0.3941,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2374907284975052,
+      "rewards/margins": 1.910300612449646,
+      "rewards/rejected": -2.1477913856506348,
+      "step": 80
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "eval_logits/chosen": -1.9900643825531006,
+      "eval_logits/rejected": -1.9449083805084229,
+      "eval_logps/chosen": -202.59437561035156,
+      "eval_logps/rejected": -221.12725830078125,
+      "eval_loss": 0.4217630624771118,
+      "eval_rewards/accuracies": 0.8044354915618896,
+      "eval_rewards/chosen": -0.22749020159244537,
+      "eval_rewards/margins": 2.0644266605377197,
+      "eval_rewards/rejected": -2.291916847229004,
+      "eval_runtime": 247.3121,
+      "eval_samples_per_second": 15.859,
+      "eval_steps_per_second": 0.251,
+      "step": 80
+    },
+    {
+      "epoch": 0.6159420289855072,
+      "grad_norm": 34.207898226903815,
+      "learning_rate": 9.173478150725651e-07,
+      "logits/chosen": -2.0169568061828613,
+      "logits/rejected": -1.9391515254974365,
+      "logps/chosen": -209.73440551757812,
+      "logps/rejected": -215.14205932617188,
+      "loss": 0.422,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.1130056157708168,
+      "rewards/margins": 2.3998470306396484,
+      "rewards/rejected": -2.2868411540985107,
+      "step": 85
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 28.850805260840193,
+      "learning_rate": 9.063289569141251e-07,
+      "logits/chosen": -2.1180360317230225,
+      "logits/rejected": -2.080235242843628,
+      "logps/chosen": -214.2292022705078,
+      "logps/rejected": -223.37564086914062,
+      "loss": 0.4135,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.5250645279884338,
+      "rewards/margins": 2.2779579162597656,
+      "rewards/rejected": -1.7528936862945557,
+      "step": 90
+    },
+    {
+      "epoch": 0.6884057971014492,
+      "grad_norm": 34.73111091101309,
+      "learning_rate": 8.946959125124051e-07,
+      "logits/chosen": -2.2047152519226074,
+      "logits/rejected": -2.1581788063049316,
+      "logps/chosen": -209.3234405517578,
+      "logps/rejected": -195.6946563720703,
+      "loss": 0.4077,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.25443512201309204,
+      "rewards/margins": 2.2029635906219482,
+      "rewards/rejected": -1.948528528213501,
+      "step": 95
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 32.202226649445414,
+      "learning_rate": 8.824662657873238e-07,
+      "logits/chosen": -2.256134510040283,
+      "logits/rejected": -2.2395310401916504,
+      "logps/chosen": -176.19464111328125,
+      "logps/rejected": -209.0999298095703,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3457742929458618,
+      "rewards/margins": 1.9383150339126587,
+      "rewards/rejected": -2.2840893268585205,
+      "step": 100
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 31.35693490170537,
+      "learning_rate": 8.696585024526135e-07,
+      "logits/chosen": -2.3358142375946045,
+      "logits/rejected": -2.307068347930908,
+      "logps/chosen": -191.8298797607422,
+      "logps/rejected": -227.55612182617188,
+      "loss": 0.4017,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.2825666069984436,
+      "rewards/margins": 2.5402400493621826,
+      "rewards/rejected": -2.8228065967559814,
+      "step": 105
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 36.29919961993296,
+      "learning_rate": 8.562919820737535e-07,
+      "logits/chosen": -2.2931602001190186,
+      "logits/rejected": -2.2568557262420654,
+      "logps/chosen": -207.34158325195312,
+      "logps/rejected": -208.9143524169922,
+      "loss": 0.3767,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.3017815351486206,
+      "rewards/margins": 2.3830084800720215,
+      "rewards/rejected": -2.6847901344299316,
+      "step": 110
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 28.819478551304137,
+      "learning_rate": 8.423869088050315e-07,
+      "logits/chosen": -2.2734763622283936,
+      "logits/rejected": -2.2522785663604736,
+      "logps/chosen": -195.6924591064453,
+      "logps/rejected": -221.85104370117188,
+      "loss": 0.3892,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.12773282825946808,
+      "rewards/margins": 2.3888843059539795,
+      "rewards/rejected": -2.5166170597076416,
+      "step": 115
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 37.085951928654964,
+      "learning_rate": 8.2796430084997e-07,
+      "logits/chosen": -2.2070839405059814,
+      "logits/rejected": -2.1736464500427246,
+      "logps/chosen": -196.70889282226562,
+      "logps/rejected": -207.93417358398438,
+      "loss": 0.3717,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.12862932682037354,
+      "rewards/margins": 2.698848009109497,
+      "rewards/rejected": -2.570218563079834,
+      "step": 120
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_logits/chosen": -2.122933864593506,
+      "eval_logits/rejected": -2.0901710987091064,
+      "eval_logps/chosen": -202.4208221435547,
+      "eval_logps/rejected": -223.09356689453125,
+      "eval_loss": 0.438678115606308,
+      "eval_rewards/accuracies": 0.8286290168762207,
+      "eval_rewards/chosen": -0.2101391851902008,
+      "eval_rewards/margins": 2.278407573699951,
+      "eval_rewards/rejected": -2.488546848297119,
+      "eval_runtime": 247.3754,
+      "eval_samples_per_second": 15.854,
+      "eval_steps_per_second": 0.251,
+      "step": 120
+    },
+    {
+      "epoch": 0.9057971014492754,
+      "grad_norm": 27.843666767086823,
+      "learning_rate": 8.130459586912753e-07,
+      "logits/chosen": -2.0930094718933105,
+      "logits/rejected": -2.0791330337524414,
+      "logps/chosen": -220.4320526123047,
+      "logps/rejected": -218.3594512939453,
+      "loss": 0.4575,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.9592973589897156,
+      "rewards/margins": 1.66092050075531,
+      "rewards/rejected": -2.620218276977539,
+      "step": 125
+    },
+    {
+      "epoch": 0.9420289855072463,
+      "grad_norm": 28.902451958691426,
+      "learning_rate": 7.97654432138333e-07,
+      "logits/chosen": -2.1393418312072754,
+      "logits/rejected": -2.103482723236084,
+      "logps/chosen": -214.5059051513672,
+      "logps/rejected": -248.8673858642578,
+      "loss": 0.388,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.1911260336637497,
+      "rewards/margins": 2.8205361366271973,
+      "rewards/rejected": -3.011662006378174,
+      "step": 130
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 26.45174989804514,
+      "learning_rate": 7.81812986242061e-07,
+      "logits/chosen": -2.2018837928771973,
+      "logits/rejected": -2.1459240913391113,
+      "logps/chosen": -193.5723419189453,
+      "logps/rejected": -233.81838989257812,
+      "loss": 0.365,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": 0.10008885711431503,
+      "rewards/margins": 3.072911262512207,
+      "rewards/rejected": -2.972822427749634,
+      "step": 135
+    },
+    {
+      "epoch": 1.0144927536231885,
+      "grad_norm": 16.755101670108846,
+      "learning_rate": 7.655455661286375e-07,
+      "logits/chosen": -2.190566301345825,
+      "logits/rejected": -2.1852922439575195,
+      "logps/chosen": -190.56027221679688,
+      "logps/rejected": -234.6202392578125,
+      "loss": 0.2524,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 0.05487387627363205,
+      "rewards/margins": 3.58606219291687,
+      "rewards/rejected": -3.531188488006592,
+      "step": 140
+    },
+    {
+      "epoch": 1.0507246376811594,
+      "grad_norm": 16.022443175608785,
+      "learning_rate": 7.488767608052628e-07,
+      "logits/chosen": -2.2735958099365234,
+      "logits/rejected": -2.199552059173584,
+      "logps/chosen": -190.21511840820312,
+      "logps/rejected": -237.59854125976562,
+      "loss": 0.171,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.7184330821037292,
+      "rewards/margins": 4.115548133850098,
+      "rewards/rejected": -3.3971149921417236,
+      "step": 145
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 16.37925141930124,
+      "learning_rate": 7.318317659926636e-07,
+      "logits/chosen": -2.250054121017456,
+      "logits/rejected": -2.221043109893799,
+      "logps/chosen": -174.0218048095703,
+      "logps/rejected": -237.14120483398438,
+      "loss": 0.1436,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 1.0139648914337158,
+      "rewards/margins": 4.169236660003662,
+      "rewards/rejected": -3.1552722454071045,
+      "step": 150
+    },
+    {
+      "epoch": 1.1231884057971016,
+      "grad_norm": 13.693805739113818,
+      "learning_rate": 7.144363460405189e-07,
+      "logits/chosen": -2.3314082622528076,
+      "logits/rejected": -2.2712883949279785,
+      "logps/chosen": -192.2017059326172,
+      "logps/rejected": -236.91586303710938,
+      "loss": 0.1415,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 1.1952037811279297,
+      "rewards/margins": 4.705626487731934,
+      "rewards/rejected": -3.510422945022583,
+      "step": 155
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 13.203700040695288,
+      "learning_rate": 6.967167949833762e-07,
+      "logits/chosen": -2.324735164642334,
+      "logits/rejected": -2.283231258392334,
+      "logps/chosen": -194.0807342529297,
+      "logps/rejected": -247.2218475341797,
+      "loss": 0.1459,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.3761358857154846,
+      "rewards/margins": 4.9711785316467285,
+      "rewards/rejected": -4.595042705535889,
+      "step": 160
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "eval_logits/chosen": -2.3007450103759766,
+      "eval_logits/rejected": -2.273284673690796,
+      "eval_logps/chosen": -204.34878540039062,
+      "eval_logps/rejected": -232.13629150390625,
+      "eval_loss": 0.42876046895980835,
+      "eval_rewards/accuracies": 0.8286290168762207,
+      "eval_rewards/chosen": -0.40293240547180176,
+      "eval_rewards/margins": 2.9898877143859863,
+      "eval_rewards/rejected": -3.392819881439209,
+      "eval_runtime": 247.3207,
+      "eval_samples_per_second": 15.858,
+      "eval_steps_per_second": 0.251,
+      "step": 160
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 17.287170066985027,
+      "learning_rate": 6.786998967959219e-07,
+      "logits/chosen": -2.313910961151123,
+      "logits/rejected": -2.274190902709961,
+      "logps/chosen": -200.9847869873047,
+      "logps/rejected": -228.14138793945312,
+      "loss": 0.1497,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.39603787660598755,
+      "rewards/margins": 4.507396697998047,
+      "rewards/rejected": -4.111359119415283,
+      "step": 165
+    },
+    {
+      "epoch": 1.2318840579710144,
+      "grad_norm": 16.43946047429659,
+      "learning_rate": 6.604128849076838e-07,
+      "logits/chosen": -2.340721607208252,
+      "logits/rejected": -2.305487871170044,
+      "logps/chosen": -200.94406127929688,
+      "logps/rejected": -238.47921752929688,
+      "loss": 0.1533,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.9461654424667358,
+      "rewards/margins": 4.6484904289245605,
+      "rewards/rejected": -3.702324390411377,
+      "step": 170
+    },
+    {
+      "epoch": 1.2681159420289856,
+      "grad_norm": 13.545354366232296,
+      "learning_rate": 6.418834010383609e-07,
+      "logits/chosen": -2.400474786758423,
+      "logits/rejected": -2.343231439590454,
+      "logps/chosen": -172.61148071289062,
+      "logps/rejected": -230.24197387695312,
+      "loss": 0.1459,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.5564432144165039,
+      "rewards/margins": 4.526711463928223,
+      "rewards/rejected": -3.9702675342559814,
+      "step": 175
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 16.208760712520707,
+      "learning_rate": 6.231394534160007e-07,
+      "logits/chosen": -2.3880228996276855,
+      "logits/rejected": -2.377924680709839,
+      "logps/chosen": -186.1154327392578,
+      "logps/rejected": -228.6842498779297,
+      "loss": 0.1408,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 1.147924542427063,
+      "rewards/margins": 4.681893348693848,
+      "rewards/rejected": -3.533968687057495,
+      "step": 180
+    },
+    {
+      "epoch": 1.3405797101449275,
+      "grad_norm": 16.391749704364813,
+      "learning_rate": 6.042093744411828e-07,
+      "logits/chosen": -2.3000502586364746,
+      "logits/rejected": -2.280015468597412,
+      "logps/chosen": -184.9687042236328,
+      "logps/rejected": -230.6714630126953,
+      "loss": 0.1426,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 1.1101362705230713,
+      "rewards/margins": 4.539022922515869,
+      "rewards/rejected": -3.4288864135742188,
+      "step": 185
+    },
+    {
+      "epoch": 1.3768115942028984,
+      "grad_norm": 15.103230138315158,
+      "learning_rate": 5.851217778611993e-07,
+      "logits/chosen": -2.2735018730163574,
+      "logits/rejected": -2.272218942642212,
+      "logps/chosen": -196.11097717285156,
+      "logps/rejected": -217.5700225830078,
+      "loss": 0.1351,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.8358832597732544,
+      "rewards/margins": 4.623397350311279,
+      "rewards/rejected": -3.7875142097473145,
+      "step": 190
+    },
+    {
+      "epoch": 1.4130434782608696,
+      "grad_norm": 23.621795316466446,
+      "learning_rate": 5.659055155189651e-07,
+      "logits/chosen": -2.325028896331787,
+      "logits/rejected": -2.252711296081543,
+      "logps/chosen": -193.0414276123047,
+      "logps/rejected": -231.9776611328125,
+      "loss": 0.1542,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.06639621406793594,
+      "rewards/margins": 4.913178443908691,
+      "rewards/rejected": -4.8467817306518555,
+      "step": 195
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 11.913033785498357,
+      "learning_rate": 5.465896337420358e-07,
+      "logits/chosen": -2.3189964294433594,
+      "logits/rejected": -2.2462618350982666,
+      "logps/chosen": -207.55685424804688,
+      "logps/rejected": -269.5002746582031,
+      "loss": 0.1455,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 0.3675020635128021,
+      "rewards/margins": 5.308381080627441,
+      "rewards/rejected": -4.940878868103027,
+      "step": 200
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "eval_logits/chosen": -2.2696547508239746,
+      "eval_logits/rejected": -2.246581554412842,
+      "eval_logps/chosen": -205.6576690673828,
+      "eval_logps/rejected": -234.53866577148438,
+      "eval_loss": 0.42552247643470764,
+      "eval_rewards/accuracies": 0.8165322542190552,
+      "eval_rewards/chosen": -0.5338226556777954,
+      "eval_rewards/margins": 3.099236011505127,
+      "eval_rewards/rejected": -3.633058547973633,
+      "eval_runtime": 247.2511,
+      "eval_samples_per_second": 15.862,
+      "eval_steps_per_second": 0.251,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2358113407598592.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af79ff24bae38840a3c8efe3d28d0cc2a77ca640996f1dd8521f5747a2625682
+size 7096

checkpoint-240/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-240/config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/data/align-anything/hantao/models/llava-v1.6-mistral-7b-hf",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}