Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- config.json +53 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +449 -0
- quantize_config.json +23 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</think>": 151668,
|
3 |
+
"</tool_call>": 151658,
|
4 |
+
"</tool_response>": 151666,
|
5 |
+
"<think>": 151667,
|
6 |
+
"<tool_call>": 151657,
|
7 |
+
"<tool_response>": 151665,
|
8 |
+
"<|box_end|>": 151649,
|
9 |
+
"<|box_start|>": 151648,
|
10 |
+
"<|endoftext|>": 151643,
|
11 |
+
"<|file_sep|>": 151664,
|
12 |
+
"<|fim_middle|>": 151660,
|
13 |
+
"<|fim_pad|>": 151662,
|
14 |
+
"<|fim_prefix|>": 151659,
|
15 |
+
"<|fim_suffix|>": 151661,
|
16 |
+
"<|im_end|>": 151645,
|
17 |
+
"<|im_start|>": 151644,
|
18 |
+
"<|image_pad|>": 151655,
|
19 |
+
"<|object_ref_end|>": 151647,
|
20 |
+
"<|object_ref_start|>": 151646,
|
21 |
+
"<|quad_end|>": 151651,
|
22 |
+
"<|quad_start|>": 151650,
|
23 |
+
"<|repo_name|>": 151663,
|
24 |
+
"<|video_pad|>": 151656,
|
25 |
+
"<|vision_end|>": 151653,
|
26 |
+
"<|vision_pad|>": 151654,
|
27 |
+
"<|vision_start|>": 151652
|
28 |
+
}
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 25600,
|
14 |
+
"max_position_embeddings": 40960,
|
15 |
+
"max_window_layers": 64,
|
16 |
+
"model_type": "qwen3",
|
17 |
+
"num_attention_heads": 64,
|
18 |
+
"num_hidden_layers": 64,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"quantization_config": {
|
21 |
+
"bits": 4,
|
22 |
+
"checkpoint_format": "gptq",
|
23 |
+
"desc_act": true,
|
24 |
+
"group_size": 128,
|
25 |
+
"lm_head": false,
|
26 |
+
"meta": {
|
27 |
+
"damp_auto_increment": 0.0025,
|
28 |
+
"damp_percent": 0.01,
|
29 |
+
"mse": 0.0,
|
30 |
+
"quantizer": [
|
31 |
+
"gptqmodel:3.1.0-dev"
|
32 |
+
],
|
33 |
+
"static_groups": false,
|
34 |
+
"true_sequential": true,
|
35 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
36 |
+
"v2": false,
|
37 |
+
"v2_alpha": 0.25
|
38 |
+
},
|
39 |
+
"pack_dtype": "int32",
|
40 |
+
"quant_method": "gptq",
|
41 |
+
"sym": true
|
42 |
+
},
|
43 |
+
"rms_norm_eps": 1e-06,
|
44 |
+
"rope_scaling": null,
|
45 |
+
"rope_theta": 1000000,
|
46 |
+
"sliding_window": null,
|
47 |
+
"tie_word_embeddings": false,
|
48 |
+
"torch_dtype": "bfloat16",
|
49 |
+
"transformers_version": "4.51.3",
|
50 |
+
"use_cache": true,
|
51 |
+
"use_sliding_window": false,
|
52 |
+
"vocab_size": 151936
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_k": 20,
|
11 |
+
"top_p": 0.95,
|
12 |
+
"transformers_version": "4.51.3"
|
13 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e4b74381406477646b80776ee2b8d0c3913175139564a8d720fe13f81d85a9
|
3 |
+
size 3955280848
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cafa042b79265530390064da0f11aefb4c3b5da8f2f790e84e621b60dce9b94
|
3 |
+
size 3989151776
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e567661c327ce78864e25b7cd95f32e88e0da25f091767af9c7e7cbd5da56689
|
3 |
+
size 3939923288
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:417a5212f6e99f5ff915e0549c172379a0afe5115c182db85fa762fc00060801
|
3 |
+
size 3989151824
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2fe424400ac8fb324e6db7d7f37af9a8e8be76f911bc0f7574cc53cbb1c840a
|
3 |
+
size 3467226552
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quant_log.csv
ADDED
@@ -0,0 +1,449 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.0000000017,0.01000,2.788
|
3 |
+
0,self_attn.v_proj,0.0000000014,0.01000,1.527
|
4 |
+
0,self_attn.q_proj,0.0000000088,0.01000,1.565
|
5 |
+
0,self_attn.o_proj,0.0000000606,0.01000,2.580
|
6 |
+
0,mlp.gate_proj,0.0000001939,0.01000,1.655
|
7 |
+
0,mlp.up_proj,0.0000001738,0.01000,1.661
|
8 |
+
0,mlp.down_proj,0.0000003078,0.01000,11.545
|
9 |
+
1,self_attn.k_proj,0.0000000026,0.01000,1.520
|
10 |
+
1,self_attn.v_proj,0.0000000024,0.01000,1.537
|
11 |
+
1,self_attn.q_proj,0.0000000154,0.01000,1.572
|
12 |
+
1,self_attn.o_proj,0.0000000438,0.01000,2.613
|
13 |
+
1,mlp.gate_proj,0.0000136234,0.01000,1.663
|
14 |
+
1,mlp.up_proj,0.0000043194,0.01000,1.668
|
15 |
+
1,mlp.down_proj,0.0000015933,0.01000,11.733
|
16 |
+
2,self_attn.k_proj,0.0000000047,0.01000,1.518
|
17 |
+
2,self_attn.v_proj,0.0000000047,0.01000,1.533
|
18 |
+
2,self_attn.q_proj,0.0000000251,0.01000,1.570
|
19 |
+
2,self_attn.o_proj,0.0000000731,0.01000,2.610
|
20 |
+
2,mlp.gate_proj,0.0000210778,0.01000,1.647
|
21 |
+
2,mlp.up_proj,0.0000090475,0.01000,1.658
|
22 |
+
2,mlp.down_proj,0.0000236344,0.01000,11.642
|
23 |
+
3,self_attn.k_proj,0.0000000093,0.01000,1.582
|
24 |
+
3,self_attn.v_proj,0.0000000092,0.01000,1.528
|
25 |
+
3,self_attn.q_proj,0.0000000510,0.01000,1.573
|
26 |
+
3,self_attn.o_proj,0.0000000874,0.01000,2.583
|
27 |
+
3,mlp.gate_proj,0.0000342387,0.01000,1.657
|
28 |
+
3,mlp.up_proj,0.0000152574,0.01000,1.662
|
29 |
+
3,mlp.down_proj,0.0000022079,0.01000,11.685
|
30 |
+
4,self_attn.k_proj,0.0000000162,0.01000,1.518
|
31 |
+
4,self_attn.v_proj,0.0000000155,0.01000,1.521
|
32 |
+
4,self_attn.q_proj,0.0000000928,0.01000,1.557
|
33 |
+
4,self_attn.o_proj,0.0000001252,0.01000,2.585
|
34 |
+
4,mlp.gate_proj,0.0000526053,0.01000,1.647
|
35 |
+
4,mlp.up_proj,0.0000299418,0.01000,1.654
|
36 |
+
4,mlp.down_proj,0.0000022912,0.01000,11.655
|
37 |
+
5,self_attn.k_proj,0.0000000200,0.01000,1.522
|
38 |
+
5,self_attn.v_proj,0.0000000170,0.01000,1.552
|
39 |
+
5,self_attn.q_proj,0.0000001186,0.01000,1.559
|
40 |
+
5,self_attn.o_proj,0.0000001177,0.01000,2.598
|
41 |
+
5,mlp.gate_proj,0.0000628946,0.01000,1.648
|
42 |
+
5,mlp.up_proj,0.0000280260,0.01000,1.662
|
43 |
+
5,mlp.down_proj,0.0000032536,0.01000,11.667
|
44 |
+
6,self_attn.k_proj,0.0000000270,0.01000,1.528
|
45 |
+
6,self_attn.v_proj,0.0000000273,0.01000,1.533
|
46 |
+
6,self_attn.q_proj,0.0000001575,0.01000,1.566
|
47 |
+
6,self_attn.o_proj,0.0000001395,0.01000,2.590
|
48 |
+
6,mlp.gate_proj,0.0001220081,0.01000,1.651
|
49 |
+
6,mlp.up_proj,0.0000689582,0.01000,1.668
|
50 |
+
6,mlp.down_proj,0.0001097991,0.01000,11.715
|
51 |
+
7,self_attn.k_proj,0.0000001808,0.01000,1.532
|
52 |
+
7,self_attn.v_proj,0.0000001897,0.01000,1.570
|
53 |
+
7,self_attn.q_proj,0.0000010704,0.01000,1.575
|
54 |
+
7,self_attn.o_proj,0.0000004539,0.01000,2.633
|
55 |
+
7,mlp.gate_proj,0.0001435714,0.01000,1.664
|
56 |
+
7,mlp.up_proj,0.0000800578,0.01000,1.677
|
57 |
+
7,mlp.down_proj,0.0000048121,0.01000,11.737
|
58 |
+
8,self_attn.k_proj,0.0000001726,0.01000,1.539
|
59 |
+
8,self_attn.v_proj,0.0000001859,0.01000,1.584
|
60 |
+
8,self_attn.q_proj,0.0000009734,0.01000,1.573
|
61 |
+
8,self_attn.o_proj,0.0000004123,0.01000,2.612
|
62 |
+
8,mlp.gate_proj,0.0000358017,0.01000,1.665
|
63 |
+
8,mlp.up_proj,0.0000214317,0.01000,1.677
|
64 |
+
8,mlp.down_proj,0.0000034534,0.01000,11.681
|
65 |
+
9,self_attn.k_proj,0.0000000908,0.01000,1.526
|
66 |
+
9,self_attn.v_proj,0.0000000840,0.01000,1.534
|
67 |
+
9,self_attn.q_proj,0.0000005153,0.01000,1.570
|
68 |
+
9,self_attn.o_proj,0.0000002444,0.01000,2.612
|
69 |
+
9,mlp.gate_proj,0.0000200863,0.01000,1.661
|
70 |
+
9,mlp.up_proj,0.0000190404,0.01000,1.660
|
71 |
+
9,mlp.down_proj,0.0000045632,0.01000,11.628
|
72 |
+
10,self_attn.k_proj,0.0000001602,0.01000,1.533
|
73 |
+
10,self_attn.v_proj,0.0000001714,0.01000,1.570
|
74 |
+
10,self_attn.q_proj,0.0000009465,0.01000,1.567
|
75 |
+
10,self_attn.o_proj,0.0000005223,0.01000,2.591
|
76 |
+
10,mlp.gate_proj,0.0000228654,0.01000,1.663
|
77 |
+
10,mlp.up_proj,0.0000218438,0.01000,1.672
|
78 |
+
10,mlp.down_proj,0.0000046504,0.01000,11.629
|
79 |
+
11,self_attn.k_proj,0.0000002364,0.01000,1.522
|
80 |
+
11,self_attn.v_proj,0.0000002512,0.01000,1.594
|
81 |
+
11,self_attn.q_proj,0.0000013518,0.01000,1.563
|
82 |
+
11,self_attn.o_proj,0.0000009071,0.01000,2.641
|
83 |
+
11,mlp.gate_proj,0.0000269802,0.01000,1.653
|
84 |
+
11,mlp.up_proj,0.0000257264,0.01000,1.655
|
85 |
+
11,mlp.down_proj,0.0000057269,0.01000,11.567
|
86 |
+
12,self_attn.k_proj,0.0000001623,0.01000,1.522
|
87 |
+
12,self_attn.v_proj,0.0000001594,0.01000,1.521
|
88 |
+
12,self_attn.q_proj,0.0000009575,0.01000,1.580
|
89 |
+
12,self_attn.o_proj,0.0000004861,0.01000,2.590
|
90 |
+
12,mlp.gate_proj,0.0000302366,0.01000,1.656
|
91 |
+
12,mlp.up_proj,0.0000287353,0.01000,1.685
|
92 |
+
12,mlp.down_proj,0.0000063500,0.01000,11.638
|
93 |
+
13,self_attn.k_proj,0.0000003274,0.01000,1.529
|
94 |
+
13,self_attn.v_proj,0.0000003563,0.01000,1.534
|
95 |
+
13,self_attn.q_proj,0.0000018892,0.01000,1.599
|
96 |
+
13,self_attn.o_proj,0.0000008960,0.01000,2.588
|
97 |
+
13,mlp.gate_proj,0.0000316925,0.01000,1.657
|
98 |
+
13,mlp.up_proj,0.0000293564,0.01000,1.670
|
99 |
+
13,mlp.down_proj,0.0000062898,0.01000,11.654
|
100 |
+
14,self_attn.k_proj,0.0000001693,0.01000,1.533
|
101 |
+
14,self_attn.v_proj,0.0000001780,0.01000,1.531
|
102 |
+
14,self_attn.q_proj,0.0000008925,0.01000,1.567
|
103 |
+
14,self_attn.o_proj,0.0000007708,0.01000,2.592
|
104 |
+
14,mlp.gate_proj,0.0000299584,0.01000,1.663
|
105 |
+
14,mlp.up_proj,0.0000280440,0.01000,1.676
|
106 |
+
14,mlp.down_proj,0.0000060165,0.01000,11.654
|
107 |
+
15,self_attn.k_proj,0.0000001523,0.01000,1.533
|
108 |
+
15,self_attn.v_proj,0.0000001424,0.01000,1.538
|
109 |
+
15,self_attn.q_proj,0.0000009217,0.01000,1.575
|
110 |
+
15,self_attn.o_proj,0.0000006862,0.01000,2.599
|
111 |
+
15,mlp.gate_proj,0.0000272009,0.01000,1.657
|
112 |
+
15,mlp.up_proj,0.0000260037,0.01000,1.663
|
113 |
+
15,mlp.down_proj,0.0000053479,0.01000,11.652
|
114 |
+
16,self_attn.k_proj,0.0000001507,0.01000,1.536
|
115 |
+
16,self_attn.v_proj,0.0000001643,0.01000,1.531
|
116 |
+
16,self_attn.q_proj,0.0000008906,0.01000,1.608
|
117 |
+
16,self_attn.o_proj,0.0000007135,0.01000,2.596
|
118 |
+
16,mlp.gate_proj,0.0000237589,0.01000,1.666
|
119 |
+
16,mlp.up_proj,0.0000228453,0.01000,1.665
|
120 |
+
16,mlp.down_proj,0.0000047357,0.01000,11.687
|
121 |
+
17,self_attn.k_proj,0.0000001584,0.01000,1.581
|
122 |
+
17,self_attn.v_proj,0.0000001557,0.01000,1.534
|
123 |
+
17,self_attn.q_proj,0.0000009061,0.01000,1.578
|
124 |
+
17,self_attn.o_proj,0.0000007178,0.01000,2.591
|
125 |
+
17,mlp.gate_proj,0.0000247747,0.01000,1.657
|
126 |
+
17,mlp.up_proj,0.0000236729,0.01000,1.661
|
127 |
+
17,mlp.down_proj,0.0000050207,0.01000,11.625
|
128 |
+
18,self_attn.k_proj,0.0000002016,0.01000,1.523
|
129 |
+
18,self_attn.v_proj,0.0000002049,0.01000,1.550
|
130 |
+
18,self_attn.q_proj,0.0000012114,0.01000,1.563
|
131 |
+
18,self_attn.o_proj,0.0000007100,0.01000,2.585
|
132 |
+
18,mlp.gate_proj,0.0000261823,0.01000,1.654
|
133 |
+
18,mlp.up_proj,0.0000250506,0.01000,1.662
|
134 |
+
18,mlp.down_proj,0.0000055806,0.01000,11.619
|
135 |
+
19,self_attn.k_proj,0.0000002369,0.01000,1.552
|
136 |
+
19,self_attn.v_proj,0.0000002376,0.01000,1.522
|
137 |
+
19,self_attn.q_proj,0.0000014459,0.01000,1.566
|
138 |
+
19,self_attn.o_proj,0.0000009579,0.01000,2.576
|
139 |
+
19,mlp.gate_proj,0.0000289118,0.01000,1.651
|
140 |
+
19,mlp.up_proj,0.0000277034,0.01000,1.656
|
141 |
+
19,mlp.down_proj,0.0000064796,0.01000,11.633
|
142 |
+
20,self_attn.k_proj,0.0000003935,0.01000,1.540
|
143 |
+
20,self_attn.v_proj,0.0000004184,0.01000,1.538
|
144 |
+
20,self_attn.q_proj,0.0000023191,0.01000,1.571
|
145 |
+
20,self_attn.o_proj,0.0000010780,0.01000,2.599
|
146 |
+
20,mlp.gate_proj,0.0000314793,0.01000,1.662
|
147 |
+
20,mlp.up_proj,0.0000305096,0.01000,1.663
|
148 |
+
20,mlp.down_proj,0.0000073572,0.01000,11.677
|
149 |
+
21,self_attn.k_proj,0.0000004463,0.01000,1.617
|
150 |
+
21,self_attn.v_proj,0.0000004503,0.01000,1.524
|
151 |
+
21,self_attn.q_proj,0.0000027145,0.01000,1.570
|
152 |
+
21,self_attn.o_proj,0.0000020061,0.01000,2.590
|
153 |
+
21,mlp.gate_proj,0.0000336272,0.01000,1.653
|
154 |
+
21,mlp.up_proj,0.0000325441,0.01000,1.652
|
155 |
+
21,mlp.down_proj,0.0000083934,0.01000,11.613
|
156 |
+
22,self_attn.k_proj,0.0000004100,0.01000,1.522
|
157 |
+
22,self_attn.v_proj,0.0000004306,0.01000,1.607
|
158 |
+
22,self_attn.q_proj,0.0000024698,0.01000,1.556
|
159 |
+
22,self_attn.o_proj,0.0000023926,0.01000,2.592
|
160 |
+
22,mlp.gate_proj,0.0000375279,0.01000,1.650
|
161 |
+
22,mlp.up_proj,0.0000362391,0.01000,1.654
|
162 |
+
22,mlp.down_proj,0.0000102213,0.01000,11.669
|
163 |
+
23,self_attn.k_proj,0.0000005715,0.01000,1.539
|
164 |
+
23,self_attn.v_proj,0.0000006219,0.01000,1.533
|
165 |
+
23,self_attn.q_proj,0.0000032670,0.01000,1.569
|
166 |
+
23,self_attn.o_proj,0.0000016286,0.01000,2.600
|
167 |
+
23,mlp.gate_proj,0.0000413675,0.01000,1.666
|
168 |
+
23,mlp.up_proj,0.0000401351,0.01000,1.666
|
169 |
+
23,mlp.down_proj,0.0000121474,0.01000,11.711
|
170 |
+
24,self_attn.k_proj,0.0000010734,0.01000,1.545
|
171 |
+
24,self_attn.v_proj,0.0000011345,0.01000,1.520
|
172 |
+
24,self_attn.q_proj,0.0000066250,0.01000,1.565
|
173 |
+
24,self_attn.o_proj,0.0000034682,0.01000,2.611
|
174 |
+
24,mlp.gate_proj,0.0000466318,0.01000,1.658
|
175 |
+
24,mlp.up_proj,0.0000448090,0.01000,1.656
|
176 |
+
24,mlp.down_proj,0.0000140472,0.01000,11.592
|
177 |
+
25,self_attn.k_proj,0.0000009336,0.01000,1.526
|
178 |
+
25,self_attn.v_proj,0.0000009881,0.01000,1.597
|
179 |
+
25,self_attn.q_proj,0.0000055595,0.01000,1.558
|
180 |
+
25,self_attn.o_proj,0.0000031547,0.01000,2.599
|
181 |
+
25,mlp.gate_proj,0.0000515109,0.01000,1.653
|
182 |
+
25,mlp.up_proj,0.0000498247,0.01000,1.659
|
183 |
+
25,mlp.down_proj,0.0000172977,0.01000,11.626
|
184 |
+
26,self_attn.k_proj,0.0000008480,0.01000,1.572
|
185 |
+
26,self_attn.v_proj,0.0000009399,0.01000,1.576
|
186 |
+
26,self_attn.q_proj,0.0000049706,0.01000,1.579
|
187 |
+
26,self_attn.o_proj,0.0000029387,0.01000,2.628
|
188 |
+
26,mlp.gate_proj,0.0000552996,0.01000,1.656
|
189 |
+
26,mlp.up_proj,0.0000531638,0.01000,1.663
|
190 |
+
26,mlp.down_proj,0.0000214012,0.01000,11.649
|
191 |
+
27,self_attn.k_proj,0.0000011905,0.01000,1.538
|
192 |
+
27,self_attn.v_proj,0.0000013019,0.01000,1.533
|
193 |
+
27,self_attn.q_proj,0.0000067391,0.01000,1.571
|
194 |
+
27,self_attn.o_proj,0.0000030339,0.01000,2.600
|
195 |
+
27,mlp.gate_proj,0.0000633302,0.01000,1.659
|
196 |
+
27,mlp.up_proj,0.0000603007,0.01000,1.670
|
197 |
+
27,mlp.down_proj,0.0000258225,0.01000,11.653
|
198 |
+
28,self_attn.k_proj,0.0000015645,0.01000,1.546
|
199 |
+
28,self_attn.v_proj,0.0000017532,0.01000,1.535
|
200 |
+
28,self_attn.q_proj,0.0000090750,0.01000,1.569
|
201 |
+
28,self_attn.o_proj,0.0000032175,0.01000,2.594
|
202 |
+
28,mlp.gate_proj,0.0000725752,0.01000,1.664
|
203 |
+
28,mlp.up_proj,0.0000684919,0.01000,1.666
|
204 |
+
28,mlp.down_proj,0.0000273187,0.01000,11.650
|
205 |
+
29,self_attn.k_proj,0.0000023108,0.01000,1.532
|
206 |
+
29,self_attn.v_proj,0.0000024692,0.01000,1.530
|
207 |
+
29,self_attn.q_proj,0.0000127017,0.01000,1.568
|
208 |
+
29,self_attn.o_proj,0.0000030833,0.01000,2.593
|
209 |
+
29,mlp.gate_proj,0.0000773708,0.01000,1.659
|
210 |
+
29,mlp.up_proj,0.0000713036,0.01000,1.658
|
211 |
+
29,mlp.down_proj,0.0000279486,0.01000,11.651
|
212 |
+
30,self_attn.k_proj,0.0000047851,0.01000,1.558
|
213 |
+
30,self_attn.v_proj,0.0000055002,0.01000,1.536
|
214 |
+
30,self_attn.q_proj,0.0000250751,0.01000,1.582
|
215 |
+
30,self_attn.o_proj,0.0000043227,0.01000,2.588
|
216 |
+
30,mlp.gate_proj,0.0001179844,0.01000,1.655
|
217 |
+
30,mlp.up_proj,0.0000896506,0.01000,1.662
|
218 |
+
30,mlp.down_proj,0.0000228687,0.01000,11.639
|
219 |
+
31,self_attn.k_proj,0.0000040168,0.01000,1.518
|
220 |
+
31,self_attn.v_proj,0.0000045436,0.01000,1.521
|
221 |
+
31,self_attn.q_proj,0.0000209386,0.01000,1.572
|
222 |
+
31,self_attn.o_proj,0.0000033066,0.01000,2.579
|
223 |
+
31,mlp.gate_proj,0.0002208151,0.01000,1.657
|
224 |
+
31,mlp.up_proj,0.0001648732,0.01000,1.657
|
225 |
+
31,mlp.down_proj,0.0000206442,0.01000,11.569
|
226 |
+
32,self_attn.k_proj,0.0000012243,0.01000,1.529
|
227 |
+
32,self_attn.v_proj,0.0000014233,0.01000,1.531
|
228 |
+
32,self_attn.q_proj,0.0000067717,0.01000,1.571
|
229 |
+
32,self_attn.o_proj,0.0000030547,0.01000,2.586
|
230 |
+
32,mlp.gate_proj,0.0001175058,0.01000,1.663
|
231 |
+
32,mlp.up_proj,0.0000903383,0.01000,1.662
|
232 |
+
32,mlp.down_proj,0.0000251651,0.01000,11.671
|
233 |
+
33,self_attn.k_proj,0.0000009662,0.01000,1.592
|
234 |
+
33,self_attn.v_proj,0.0000008725,0.01000,1.535
|
235 |
+
33,self_attn.q_proj,0.0000053462,0.01000,1.579
|
236 |
+
33,self_attn.o_proj,0.0000023472,0.01000,2.606
|
237 |
+
33,mlp.gate_proj,0.0000844701,0.01000,1.672
|
238 |
+
33,mlp.up_proj,0.0000789202,0.01000,1.665
|
239 |
+
33,mlp.down_proj,0.0000279038,0.01000,11.713
|
240 |
+
34,self_attn.k_proj,0.0000014015,0.01000,1.545
|
241 |
+
34,self_attn.v_proj,0.0000014559,0.01000,1.536
|
242 |
+
34,self_attn.q_proj,0.0000080948,0.01000,1.583
|
243 |
+
34,self_attn.o_proj,0.0000035278,0.01000,2.592
|
244 |
+
34,mlp.gate_proj,0.0000785616,0.01000,1.662
|
245 |
+
34,mlp.up_proj,0.0000756801,0.01000,1.669
|
246 |
+
34,mlp.down_proj,0.0000235830,0.01000,11.738
|
247 |
+
35,self_attn.k_proj,0.0000016930,0.01000,1.624
|
248 |
+
35,self_attn.v_proj,0.0000018099,0.01000,1.534
|
249 |
+
35,self_attn.q_proj,0.0000101715,0.01000,1.576
|
250 |
+
35,self_attn.o_proj,0.0000055023,0.01000,2.602
|
251 |
+
35,mlp.gate_proj,0.0000872563,0.01000,1.662
|
252 |
+
35,mlp.up_proj,0.0000841638,0.01000,1.668
|
253 |
+
35,mlp.down_proj,0.0000270447,0.01000,11.702
|
254 |
+
36,self_attn.k_proj,0.0000010704,0.01000,1.533
|
255 |
+
36,self_attn.v_proj,0.0000010415,0.01000,1.534
|
256 |
+
36,self_attn.q_proj,0.0000064894,0.01000,1.590
|
257 |
+
36,self_attn.o_proj,0.0000042677,0.01000,2.603
|
258 |
+
36,mlp.gate_proj,0.0000936115,0.01000,1.661
|
259 |
+
36,mlp.up_proj,0.0000906560,0.01000,1.674
|
260 |
+
36,mlp.down_proj,0.0000306681,0.01000,11.688
|
261 |
+
37,self_attn.k_proj,0.0000021818,0.01000,1.536
|
262 |
+
37,self_attn.v_proj,0.0000022700,0.01000,1.534
|
263 |
+
37,self_attn.q_proj,0.0000132923,0.01000,1.591
|
264 |
+
37,self_attn.o_proj,0.0000076662,0.01000,2.604
|
265 |
+
37,mlp.gate_proj,0.0001003652,0.01000,1.661
|
266 |
+
37,mlp.up_proj,0.0000937617,0.01000,1.670
|
267 |
+
37,mlp.down_proj,0.0000311588,0.01000,11.725
|
268 |
+
38,self_attn.k_proj,0.0000014607,0.01000,1.533
|
269 |
+
38,self_attn.v_proj,0.0000014135,0.01000,1.544
|
270 |
+
38,self_attn.q_proj,0.0000085849,0.01000,1.574
|
271 |
+
38,self_attn.o_proj,0.0000062944,0.01000,2.626
|
272 |
+
38,mlp.gate_proj,0.0000888707,0.01000,1.665
|
273 |
+
38,mlp.up_proj,0.0000865433,0.01000,1.669
|
274 |
+
38,mlp.down_proj,0.0000298793,0.01000,11.702
|
275 |
+
39,self_attn.k_proj,0.0000013231,0.01000,1.530
|
276 |
+
39,self_attn.v_proj,0.0000013062,0.01000,1.552
|
277 |
+
39,self_attn.q_proj,0.0000080722,0.01000,1.573
|
278 |
+
39,self_attn.o_proj,0.0000057884,0.01000,2.635
|
279 |
+
39,mlp.gate_proj,0.0000803082,0.01000,1.663
|
280 |
+
39,mlp.up_proj,0.0000832085,0.01000,1.669
|
281 |
+
39,mlp.down_proj,0.0000285743,0.01000,11.683
|
282 |
+
40,self_attn.k_proj,0.0000015940,0.01000,1.529
|
283 |
+
40,self_attn.v_proj,0.0000016831,0.01000,1.570
|
284 |
+
40,self_attn.q_proj,0.0000097793,0.01000,1.568
|
285 |
+
40,self_attn.o_proj,0.0000074035,0.01000,2.596
|
286 |
+
40,mlp.gate_proj,0.0000683258,0.01000,1.660
|
287 |
+
40,mlp.up_proj,0.0000740553,0.01000,1.670
|
288 |
+
40,mlp.down_proj,0.0000274739,0.01000,11.688
|
289 |
+
41,self_attn.k_proj,0.0000015246,0.01000,1.532
|
290 |
+
41,self_attn.v_proj,0.0000015665,0.01000,1.591
|
291 |
+
41,self_attn.q_proj,0.0000097473,0.01000,1.575
|
292 |
+
41,self_attn.o_proj,0.0000076067,0.01000,2.597
|
293 |
+
41,mlp.gate_proj,0.0000696800,0.01000,1.664
|
294 |
+
41,mlp.up_proj,0.0000769974,0.01000,1.667
|
295 |
+
41,mlp.down_proj,0.0000275727,0.01000,11.741
|
296 |
+
42,self_attn.k_proj,0.0000020490,0.01000,1.537
|
297 |
+
42,self_attn.v_proj,0.0000022060,0.01000,1.615
|
298 |
+
42,self_attn.q_proj,0.0000133186,0.01000,1.569
|
299 |
+
42,self_attn.o_proj,0.0000084157,0.01000,2.609
|
300 |
+
42,mlp.gate_proj,0.0000717687,0.01000,1.658
|
301 |
+
42,mlp.up_proj,0.0000811034,0.01000,1.670
|
302 |
+
42,mlp.down_proj,0.0000293940,0.01000,11.735
|
303 |
+
43,self_attn.k_proj,0.0000030497,0.01000,1.527
|
304 |
+
43,self_attn.v_proj,0.0000032869,0.01000,1.533
|
305 |
+
43,self_attn.q_proj,0.0000183930,0.01000,1.579
|
306 |
+
43,self_attn.o_proj,0.0000093715,0.01000,2.575
|
307 |
+
43,mlp.gate_proj,0.0000801787,0.01000,1.657
|
308 |
+
43,mlp.up_proj,0.0000884538,0.01000,1.661
|
309 |
+
43,mlp.down_proj,0.0004439881,0.01000,11.732
|
310 |
+
44,self_attn.k_proj,0.0000045039,0.01000,1.538
|
311 |
+
44,self_attn.v_proj,0.0000052618,0.01000,1.535
|
312 |
+
44,self_attn.q_proj,0.0000302576,0.01000,1.568
|
313 |
+
44,self_attn.o_proj,0.0000131572,0.01000,2.605
|
314 |
+
44,mlp.gate_proj,0.0000831303,0.01000,1.664
|
315 |
+
44,mlp.up_proj,0.0000927039,0.01000,1.661
|
316 |
+
44,mlp.down_proj,0.0000374299,0.01000,11.632
|
317 |
+
45,self_attn.k_proj,0.0000047013,0.01000,1.542
|
318 |
+
45,self_attn.v_proj,0.0000046386,0.01000,1.535
|
319 |
+
45,self_attn.q_proj,0.0000280581,0.01000,1.570
|
320 |
+
45,self_attn.o_proj,0.0000166424,0.01000,2.573
|
321 |
+
45,mlp.gate_proj,0.0000867418,0.01000,1.654
|
322 |
+
45,mlp.up_proj,0.0000949675,0.01000,1.658
|
323 |
+
45,mlp.down_proj,0.0000394787,0.01000,11.647
|
324 |
+
46,self_attn.k_proj,0.0000043364,0.01000,1.579
|
325 |
+
46,self_attn.v_proj,0.0000051131,0.01000,1.532
|
326 |
+
46,self_attn.q_proj,0.0000281403,0.01000,1.569
|
327 |
+
46,self_attn.o_proj,0.0000154446,0.01000,2.593
|
328 |
+
46,mlp.gate_proj,0.0000926777,0.01000,1.658
|
329 |
+
46,mlp.up_proj,0.0001016089,0.01000,1.661
|
330 |
+
46,mlp.down_proj,0.0000422449,0.01000,11.659
|
331 |
+
47,self_attn.k_proj,0.0000063028,0.01000,1.530
|
332 |
+
47,self_attn.v_proj,0.0000078766,0.01000,1.530
|
333 |
+
47,self_attn.q_proj,0.0000422536,0.01000,1.616
|
334 |
+
47,self_attn.o_proj,0.0000119769,0.01000,2.606
|
335 |
+
47,mlp.gate_proj,0.0000917994,0.01000,1.660
|
336 |
+
47,mlp.up_proj,0.0001012222,0.01000,1.656
|
337 |
+
47,mlp.down_proj,0.0000483529,0.01000,11.608
|
338 |
+
48,self_attn.k_proj,0.0000072610,0.01000,1.553
|
339 |
+
48,self_attn.v_proj,0.0000086316,0.01000,1.554
|
340 |
+
48,self_attn.q_proj,0.0000501277,0.01000,1.583
|
341 |
+
48,self_attn.o_proj,0.0000204037,0.01000,2.618
|
342 |
+
48,mlp.gate_proj,0.0000983936,0.01000,1.651
|
343 |
+
48,mlp.up_proj,0.0001062408,0.01000,1.656
|
344 |
+
48,mlp.down_proj,0.0000497970,0.01000,11.574
|
345 |
+
49,self_attn.k_proj,0.0000072908,0.01000,1.526
|
346 |
+
49,self_attn.v_proj,0.0000082672,0.01000,1.533
|
347 |
+
49,self_attn.q_proj,0.0000482482,0.01000,1.568
|
348 |
+
49,self_attn.o_proj,0.0000180286,0.01000,2.595
|
349 |
+
49,mlp.gate_proj,0.0001090345,0.01000,1.660
|
350 |
+
49,mlp.up_proj,0.0001160579,0.01000,1.677
|
351 |
+
49,mlp.down_proj,0.0000671233,0.01000,11.615
|
352 |
+
50,self_attn.k_proj,0.0000078595,0.01000,1.577
|
353 |
+
50,self_attn.v_proj,0.0000095407,0.01000,1.578
|
354 |
+
50,self_attn.q_proj,0.0000537864,0.01000,1.600
|
355 |
+
50,self_attn.o_proj,0.0000179798,0.01000,2.585
|
356 |
+
50,mlp.gate_proj,0.0001245018,0.01000,1.657
|
357 |
+
50,mlp.up_proj,0.0001288223,0.01000,1.654
|
358 |
+
50,mlp.down_proj,0.0000991518,0.01000,11.557
|
359 |
+
51,self_attn.k_proj,0.0000120663,0.01000,1.560
|
360 |
+
51,self_attn.v_proj,0.0000141722,0.01000,1.560
|
361 |
+
51,self_attn.q_proj,0.0000793110,0.01000,1.579
|
362 |
+
51,self_attn.o_proj,0.0000290850,0.01000,2.578
|
363 |
+
51,mlp.gate_proj,0.0001522964,0.01000,1.646
|
364 |
+
51,mlp.up_proj,0.0001562608,0.01000,1.655
|
365 |
+
51,mlp.down_proj,0.0001451201,0.01000,11.523
|
366 |
+
52,self_attn.k_proj,0.0000177440,0.01000,1.519
|
367 |
+
52,self_attn.v_proj,0.0000227425,0.01000,1.522
|
368 |
+
52,self_attn.q_proj,0.0001201704,0.01000,1.571
|
369 |
+
52,self_attn.o_proj,0.0000339277,0.01000,2.598
|
370 |
+
52,mlp.gate_proj,0.0001896271,0.01000,1.655
|
371 |
+
52,mlp.up_proj,0.0001955561,0.01000,1.652
|
372 |
+
52,mlp.down_proj,0.0001829167,0.01000,11.537
|
373 |
+
53,self_attn.k_proj,0.0000267924,0.01000,1.593
|
374 |
+
53,self_attn.v_proj,0.0000310515,0.01000,1.596
|
375 |
+
53,self_attn.q_proj,0.0001772364,0.01000,1.591
|
376 |
+
53,self_attn.o_proj,0.0000346997,0.01000,2.570
|
377 |
+
53,mlp.gate_proj,0.0002096771,0.01000,1.650
|
378 |
+
53,mlp.up_proj,0.0002178263,0.01000,1.652
|
379 |
+
53,mlp.down_proj,0.0002640449,0.01000,11.576
|
380 |
+
54,self_attn.k_proj,0.0000413160,0.01000,1.530
|
381 |
+
54,self_attn.v_proj,0.0000514963,0.01000,1.528
|
382 |
+
54,self_attn.q_proj,0.0002652229,0.01000,1.569
|
383 |
+
54,self_attn.o_proj,0.0000610877,0.01000,2.583
|
384 |
+
54,mlp.gate_proj,0.0002725404,0.01000,1.656
|
385 |
+
54,mlp.up_proj,0.0002823621,0.01000,1.658
|
386 |
+
54,mlp.down_proj,0.0003176455,0.01000,11.565
|
387 |
+
55,self_attn.k_proj,0.0000418148,0.01000,1.530
|
388 |
+
55,self_attn.v_proj,0.0000457386,0.01000,1.595
|
389 |
+
55,self_attn.q_proj,0.0002671333,0.01000,1.562
|
390 |
+
55,self_attn.o_proj,0.0000556373,0.01000,2.599
|
391 |
+
55,mlp.gate_proj,0.0002941125,0.01000,1.656
|
392 |
+
55,mlp.up_proj,0.0003099154,0.01000,1.658
|
393 |
+
55,mlp.down_proj,0.0004200006,0.01000,11.616
|
394 |
+
56,self_attn.k_proj,0.0000757911,0.01000,1.527
|
395 |
+
56,self_attn.v_proj,0.0001022021,0.01000,1.525
|
396 |
+
56,self_attn.q_proj,0.0004798477,0.01000,1.559
|
397 |
+
56,self_attn.o_proj,0.0000605940,0.01000,2.582
|
398 |
+
56,mlp.gate_proj,0.0003321549,0.01000,1.654
|
399 |
+
56,mlp.up_proj,0.0003545168,0.01000,1.653
|
400 |
+
56,mlp.down_proj,0.0005057008,0.01000,11.506
|
401 |
+
57,self_attn.k_proj,0.0000909598,0.01000,1.528
|
402 |
+
57,self_attn.v_proj,0.0001345350,0.01000,1.547
|
403 |
+
57,self_attn.q_proj,0.0005793813,0.01000,1.565
|
404 |
+
57,self_attn.o_proj,0.0000712917,0.01000,2.644
|
405 |
+
57,mlp.gate_proj,0.0003527863,0.01000,1.659
|
406 |
+
57,mlp.up_proj,0.0003838713,0.01000,1.660
|
407 |
+
57,mlp.down_proj,0.0006151612,0.01000,11.686
|
408 |
+
58,self_attn.k_proj,0.0001611774,0.01000,1.523
|
409 |
+
58,self_attn.v_proj,0.0002164320,0.01000,1.522
|
410 |
+
58,self_attn.q_proj,0.0010283339,0.01000,1.558
|
411 |
+
58,self_attn.o_proj,0.0000739698,0.01000,2.650
|
412 |
+
58,mlp.gate_proj,0.0003952580,0.01000,1.647
|
413 |
+
58,mlp.up_proj,0.0004374086,0.01000,1.655
|
414 |
+
58,mlp.down_proj,0.0007225038,0.01000,11.617
|
415 |
+
59,self_attn.k_proj,0.0002089985,0.01000,1.526
|
416 |
+
59,self_attn.v_proj,0.0003063982,0.01000,1.525
|
417 |
+
59,self_attn.q_proj,0.0013635720,0.01000,1.560
|
418 |
+
59,self_attn.o_proj,0.0000968474,0.01000,2.592
|
419 |
+
59,mlp.gate_proj,0.0004280806,0.01000,1.655
|
420 |
+
59,mlp.up_proj,0.0004791701,0.01000,1.672
|
421 |
+
59,mlp.down_proj,0.0008960226,0.01000,11.654
|
422 |
+
60,self_attn.k_proj,0.0001992090,0.01000,1.557
|
423 |
+
60,self_attn.v_proj,0.0002532928,0.01000,1.567
|
424 |
+
60,self_attn.q_proj,0.0013149603,0.01000,1.593
|
425 |
+
60,self_attn.o_proj,0.0001869728,0.01000,2.601
|
426 |
+
60,mlp.gate_proj,0.0004562739,0.01000,1.669
|
427 |
+
60,mlp.up_proj,0.0005242452,0.01000,1.677
|
428 |
+
60,mlp.down_proj,0.0011869921,0.01000,11.614
|
429 |
+
61,self_attn.k_proj,0.0002611662,0.01000,1.520
|
430 |
+
61,self_attn.v_proj,0.0004292642,0.01000,1.524
|
431 |
+
61,self_attn.q_proj,0.0018249277,0.01000,1.563
|
432 |
+
61,self_attn.o_proj,0.0002311784,0.01000,2.574
|
433 |
+
61,mlp.gate_proj,0.0004747803,0.01000,1.651
|
434 |
+
61,mlp.up_proj,0.0005518923,0.01000,1.657
|
435 |
+
61,mlp.down_proj,0.0016891136,0.01000,11.544
|
436 |
+
62,self_attn.k_proj,0.0002829886,0.01000,1.530
|
437 |
+
62,self_attn.v_proj,0.0004230730,0.01000,1.528
|
438 |
+
62,self_attn.q_proj,0.0018683732,0.01000,1.563
|
439 |
+
62,self_attn.o_proj,0.0004166500,0.01000,2.573
|
440 |
+
62,mlp.gate_proj,0.0006017254,0.01000,1.648
|
441 |
+
62,mlp.up_proj,0.0006672592,0.01000,1.655
|
442 |
+
62,mlp.down_proj,0.0026876772,0.01000,11.545
|
443 |
+
63,self_attn.k_proj,0.0001214323,0.01000,1.594
|
444 |
+
63,self_attn.v_proj,0.0001669539,0.01000,1.570
|
445 |
+
63,self_attn.q_proj,0.0007979369,0.01000,1.578
|
446 |
+
63,self_attn.o_proj,0.0003110567,0.01000,2.592
|
447 |
+
63,mlp.gate_proj,0.0006992443,0.01000,1.655
|
448 |
+
63,mlp.up_proj,0.0007560652,0.01000,1.659
|
449 |
+
63,mlp.down_proj,0.0074282673,0.01000,11.665
|
quantize_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"sym": true,
|
6 |
+
"lm_head": false,
|
7 |
+
"quant_method": "gptq",
|
8 |
+
"checkpoint_format": "gptq",
|
9 |
+
"pack_dtype": "int32",
|
10 |
+
"meta": {
|
11 |
+
"quantizer": [
|
12 |
+
"gptqmodel:3.1.0-dev"
|
13 |
+
],
|
14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
15 |
+
"damp_percent": 0.01,
|
16 |
+
"damp_auto_increment": 0.0025,
|
17 |
+
"static_groups": false,
|
18 |
+
"true_sequential": true,
|
19 |
+
"mse": 0.0,
|
20 |
+
"v2": false,
|
21 |
+
"v2_alpha": 0.25
|
22 |
+
}
|
23 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": "<unk>"
|
25 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
3 |
+
size 11422654
|
tokenizer_config.json
ADDED
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"151665": {
|
182 |
+
"content": "<tool_response>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"151666": {
|
190 |
+
"content": "</tool_response>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"151667": {
|
198 |
+
"content": "<think>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"151668": {
|
206 |
+
"content": "</think>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
}
|
213 |
+
},
|
214 |
+
"additional_special_tokens": [
|
215 |
+
"<|im_start|>",
|
216 |
+
"<|im_end|>",
|
217 |
+
"<|object_ref_start|>",
|
218 |
+
"<|object_ref_end|>",
|
219 |
+
"<|box_start|>",
|
220 |
+
"<|box_end|>",
|
221 |
+
"<|quad_start|>",
|
222 |
+
"<|quad_end|>",
|
223 |
+
"<|vision_start|>",
|
224 |
+
"<|vision_end|>",
|
225 |
+
"<|vision_pad|>",
|
226 |
+
"<|image_pad|>",
|
227 |
+
"<|video_pad|>"
|
228 |
+
],
|
229 |
+
"bos_token": null,
|
230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
231 |
+
"clean_up_tokenization_spaces": false,
|
232 |
+
"eos_token": "<|im_end|>",
|
233 |
+
"errors": "replace",
|
234 |
+
"extra_special_tokens": {},
|
235 |
+
"model_max_length": 131072,
|
236 |
+
"pad_token": "<unk>",
|
237 |
+
"split_special_tokens": false,
|
238 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
239 |
+
"unk_token": null,
|
240 |
+
"_commit_hash": null
|
241 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|