Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +52 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +169 -0
- quant_log.json +1 -0
- quantize_config.json +22 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "/monster/data/model/Qwen2.5-0.5B-Instruct/",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Qwen2ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 151643,
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 21,
|
| 16 |
+
"model_type": "qwen2",
|
| 17 |
+
"num_attention_heads": 14,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bits": 4,
|
| 22 |
+
"checkpoint_format": "gptq",
|
| 23 |
+
"desc_act": false,
|
| 24 |
+
"dynamic": null,
|
| 25 |
+
"group_size": 32,
|
| 26 |
+
"lm_head": false,
|
| 27 |
+
"meta": {
|
| 28 |
+
"damp_auto_increment": 0.0025,
|
| 29 |
+
"damp_percent": 0.05,
|
| 30 |
+
"mse": 0.0,
|
| 31 |
+
"quantizer": [
|
| 32 |
+
"gptqmodel:1.8.0-dev"
|
| 33 |
+
],
|
| 34 |
+
"static_groups": false,
|
| 35 |
+
"true_sequential": true,
|
| 36 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 37 |
+
},
|
| 38 |
+
"pack_dtype": "int32",
|
| 39 |
+
"quant_method": "gptq",
|
| 40 |
+
"sym": true
|
| 41 |
+
},
|
| 42 |
+
"rms_norm_eps": 1e-06,
|
| 43 |
+
"rope_scaling": null,
|
| 44 |
+
"rope_theta": 1000000.0,
|
| 45 |
+
"sliding_window": null,
|
| 46 |
+
"tie_word_embeddings": true,
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"transformers_version": "4.48.1",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"use_sliding_window": false,
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5cd46db2e83ed4a8b2e362a830ed8c6e8096cb7d70e4d811ea93a1d5e8ed8d
|
| 3 |
+
size 480350384
|
quant_log.csv
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.92654,0.05000,0.383
|
| 3 |
+
0,self_attn.v_proj,0.01888,0.05000,0.240
|
| 4 |
+
0,self_attn.q_proj,5.94556,0.05000,0.247
|
| 5 |
+
0,self_attn.o_proj,0.00328,0.05000,0.243
|
| 6 |
+
0,mlp.up_proj,83.26855,0.05000,0.262
|
| 7 |
+
0,mlp.gate_proj,136.41730,0.05000,0.263
|
| 8 |
+
0,mlp.down_proj,1.34092,0.05000,1.380
|
| 9 |
+
1,self_attn.k_proj,8.95209,0.05000,0.241
|
| 10 |
+
1,self_attn.v_proj,0.85154,0.05000,0.238
|
| 11 |
+
1,self_attn.q_proj,31.03757,0.05000,0.245
|
| 12 |
+
1,self_attn.o_proj,0.58207,0.05000,0.239
|
| 13 |
+
1,mlp.up_proj,95.90676,0.05000,0.259
|
| 14 |
+
1,mlp.gate_proj,183.64766,0.05000,0.261
|
| 15 |
+
1,mlp.down_proj,1.14676,0.05000,1.345
|
| 16 |
+
2,self_attn.k_proj,17.36003,0.05000,0.242
|
| 17 |
+
2,self_attn.v_proj,2.11829,0.05000,0.246
|
| 18 |
+
2,self_attn.q_proj,59.42081,0.05000,0.248
|
| 19 |
+
2,self_attn.o_proj,0.41101,0.05000,0.252
|
| 20 |
+
2,mlp.up_proj,138.37152,0.05000,0.267
|
| 21 |
+
2,mlp.gate_proj,258.27576,0.05000,0.265
|
| 22 |
+
2,mlp.down_proj,87.07992,0.05000,1.390
|
| 23 |
+
3,self_attn.k_proj,21.04375,0.05000,0.240
|
| 24 |
+
3,self_attn.v_proj,4.92936,0.05000,0.245
|
| 25 |
+
3,self_attn.q_proj,83.55756,0.05000,0.250
|
| 26 |
+
3,self_attn.o_proj,0.64188,0.05000,0.250
|
| 27 |
+
3,mlp.up_proj,334.65601,0.05000,0.267
|
| 28 |
+
3,mlp.gate_proj,592.50232,0.05000,0.276
|
| 29 |
+
3,mlp.down_proj,152.53775,0.05000,1.373
|
| 30 |
+
4,self_attn.k_proj,12.77439,0.05000,0.239
|
| 31 |
+
4,self_attn.v_proj,5.69861,0.05000,0.240
|
| 32 |
+
4,self_attn.q_proj,61.66964,0.05000,0.244
|
| 33 |
+
4,self_attn.o_proj,1.54178,0.05000,0.243
|
| 34 |
+
4,mlp.up_proj,202.40878,0.05000,0.260
|
| 35 |
+
4,mlp.gate_proj,317.82367,0.05000,0.263
|
| 36 |
+
4,mlp.down_proj,2.41736,0.05000,1.319
|
| 37 |
+
5,self_attn.k_proj,14.18274,0.05000,0.238
|
| 38 |
+
5,self_attn.v_proj,6.86500,0.05000,0.241
|
| 39 |
+
5,self_attn.q_proj,69.48232,0.05000,0.253
|
| 40 |
+
5,self_attn.o_proj,0.91597,0.05000,0.254
|
| 41 |
+
5,mlp.up_proj,250.59880,0.05000,0.259
|
| 42 |
+
5,mlp.gate_proj,503.84485,0.05000,0.279
|
| 43 |
+
5,mlp.down_proj,2.38952,0.05000,1.385
|
| 44 |
+
6,self_attn.k_proj,13.24366,0.05000,0.249
|
| 45 |
+
6,self_attn.v_proj,3.92612,0.05000,0.244
|
| 46 |
+
6,self_attn.q_proj,57.82330,0.05000,0.256
|
| 47 |
+
6,self_attn.o_proj,0.82199,0.05000,0.248
|
| 48 |
+
6,mlp.up_proj,202.01077,0.05000,0.260
|
| 49 |
+
6,mlp.gate_proj,291.08887,0.05000,0.263
|
| 50 |
+
6,mlp.down_proj,2.34200,0.05000,1.317
|
| 51 |
+
7,self_attn.k_proj,20.47707,0.05000,0.236
|
| 52 |
+
7,self_attn.v_proj,6.82208,0.05000,0.244
|
| 53 |
+
7,self_attn.q_proj,83.89909,0.05000,0.245
|
| 54 |
+
7,self_attn.o_proj,1.38920,0.05000,0.239
|
| 55 |
+
7,mlp.up_proj,215.59988,0.05000,0.260
|
| 56 |
+
7,mlp.gate_proj,279.67908,0.05000,0.263
|
| 57 |
+
7,mlp.down_proj,2.72322,0.05000,1.318
|
| 58 |
+
8,self_attn.k_proj,15.35229,0.05000,0.240
|
| 59 |
+
8,self_attn.v_proj,5.31779,0.05000,0.242
|
| 60 |
+
8,self_attn.q_proj,72.20273,0.05000,0.243
|
| 61 |
+
8,self_attn.o_proj,2.27721,0.05000,0.250
|
| 62 |
+
8,mlp.up_proj,190.38971,0.05000,0.262
|
| 63 |
+
8,mlp.gate_proj,251.40579,0.05000,0.269
|
| 64 |
+
8,mlp.down_proj,1.84644,0.05000,1.402
|
| 65 |
+
9,self_attn.k_proj,46.89391,0.05000,0.242
|
| 66 |
+
9,self_attn.v_proj,12.24958,0.05000,0.245
|
| 67 |
+
9,self_attn.q_proj,185.18671,0.05000,0.245
|
| 68 |
+
9,self_attn.o_proj,1.13563,0.05000,0.239
|
| 69 |
+
9,mlp.up_proj,186.08925,0.05000,0.258
|
| 70 |
+
9,mlp.gate_proj,219.94760,0.05000,0.280
|
| 71 |
+
9,mlp.down_proj,1.89974,0.05000,1.314
|
| 72 |
+
10,self_attn.k_proj,12.25381,0.05000,0.236
|
| 73 |
+
10,self_attn.v_proj,8.53600,0.05000,0.240
|
| 74 |
+
10,self_attn.q_proj,61.72304,0.05000,0.244
|
| 75 |
+
10,self_attn.o_proj,2.15923,0.05000,0.244
|
| 76 |
+
10,mlp.up_proj,153.92357,0.05000,0.263
|
| 77 |
+
10,mlp.gate_proj,200.48236,0.05000,0.261
|
| 78 |
+
10,mlp.down_proj,1.46866,0.05000,1.325
|
| 79 |
+
11,self_attn.k_proj,47.32881,0.05000,0.236
|
| 80 |
+
11,self_attn.v_proj,12.32052,0.05000,0.236
|
| 81 |
+
11,self_attn.q_proj,172.02649,0.05000,0.241
|
| 82 |
+
11,self_attn.o_proj,0.99634,0.05000,0.240
|
| 83 |
+
11,mlp.up_proj,166.91438,0.05000,0.258
|
| 84 |
+
11,mlp.gate_proj,183.99411,0.05000,0.271
|
| 85 |
+
11,mlp.down_proj,2.20383,0.05000,1.308
|
| 86 |
+
12,self_attn.k_proj,10.70629,0.05000,0.234
|
| 87 |
+
12,self_attn.v_proj,6.82535,0.05000,0.237
|
| 88 |
+
12,self_attn.q_proj,58.90049,0.05000,0.240
|
| 89 |
+
12,self_attn.o_proj,2.06957,0.05000,0.240
|
| 90 |
+
12,mlp.up_proj,151.14467,0.05000,0.259
|
| 91 |
+
12,mlp.gate_proj,168.46320,0.05000,0.273
|
| 92 |
+
12,mlp.down_proj,1.57911,0.05000,1.320
|
| 93 |
+
13,self_attn.k_proj,20.42959,0.05000,0.237
|
| 94 |
+
13,self_attn.v_proj,8.33975,0.05000,0.237
|
| 95 |
+
13,self_attn.q_proj,100.85551,0.05000,0.243
|
| 96 |
+
13,self_attn.o_proj,1.29940,0.05000,0.243
|
| 97 |
+
13,mlp.up_proj,167.68123,0.05000,0.257
|
| 98 |
+
13,mlp.gate_proj,170.36960,0.05000,0.267
|
| 99 |
+
13,mlp.down_proj,1.88119,0.05000,1.320
|
| 100 |
+
14,self_attn.k_proj,12.73074,0.05000,0.240
|
| 101 |
+
14,self_attn.v_proj,11.76164,0.05000,0.237
|
| 102 |
+
14,self_attn.q_proj,77.89767,0.05000,0.240
|
| 103 |
+
14,self_attn.o_proj,3.52199,0.05000,0.241
|
| 104 |
+
14,mlp.up_proj,163.05870,0.05000,0.254
|
| 105 |
+
14,mlp.gate_proj,184.55475,0.05000,0.260
|
| 106 |
+
14,mlp.down_proj,2.35992,0.05000,1.309
|
| 107 |
+
15,self_attn.k_proj,13.67384,0.05000,0.233
|
| 108 |
+
15,self_attn.v_proj,9.17948,0.05000,0.236
|
| 109 |
+
15,self_attn.q_proj,67.20424,0.05000,0.241
|
| 110 |
+
15,self_attn.o_proj,2.04910,0.05000,0.239
|
| 111 |
+
15,mlp.up_proj,210.13235,0.05000,0.274
|
| 112 |
+
15,mlp.gate_proj,220.19116,0.05000,0.269
|
| 113 |
+
15,mlp.down_proj,3.57103,0.05000,1.396
|
| 114 |
+
16,self_attn.k_proj,29.70275,0.05000,0.244
|
| 115 |
+
16,self_attn.v_proj,24.40463,0.05000,0.251
|
| 116 |
+
16,self_attn.q_proj,166.54938,0.05000,0.241
|
| 117 |
+
16,self_attn.o_proj,1.16431,0.05000,0.251
|
| 118 |
+
16,mlp.up_proj,267.70422,0.05000,0.272
|
| 119 |
+
16,mlp.gate_proj,344.47858,0.05000,0.266
|
| 120 |
+
16,mlp.down_proj,7.87296,0.05000,1.311
|
| 121 |
+
17,self_attn.k_proj,15.50768,0.05000,0.233
|
| 122 |
+
17,self_attn.v_proj,14.58982,0.05000,0.236
|
| 123 |
+
17,self_attn.q_proj,101.04700,0.05000,0.241
|
| 124 |
+
17,self_attn.o_proj,1.79011,0.05000,0.240
|
| 125 |
+
17,mlp.up_proj,316.87897,0.05000,0.268
|
| 126 |
+
17,mlp.gate_proj,487.06854,0.05000,0.274
|
| 127 |
+
17,mlp.down_proj,5.82991,0.05000,1.393
|
| 128 |
+
18,self_attn.k_proj,16.92690,0.05000,0.250
|
| 129 |
+
18,self_attn.v_proj,14.79226,0.05000,0.245
|
| 130 |
+
18,self_attn.q_proj,90.39028,0.05000,0.245
|
| 131 |
+
18,self_attn.o_proj,2.17428,0.05000,0.245
|
| 132 |
+
18,mlp.up_proj,308.24667,0.05000,0.257
|
| 133 |
+
18,mlp.gate_proj,386.23010,0.05000,0.265
|
| 134 |
+
18,mlp.down_proj,5.66360,0.05000,1.328
|
| 135 |
+
19,self_attn.k_proj,15.91953,0.05000,0.239
|
| 136 |
+
19,self_attn.v_proj,15.05818,0.05000,0.239
|
| 137 |
+
19,self_attn.q_proj,97.57352,0.05000,0.242
|
| 138 |
+
19,self_attn.o_proj,2.65458,0.05000,0.240
|
| 139 |
+
19,mlp.up_proj,457.87988,0.05000,0.259
|
| 140 |
+
19,mlp.gate_proj,545.14697,0.05000,0.265
|
| 141 |
+
19,mlp.down_proj,13.83433,0.05000,1.321
|
| 142 |
+
20,self_attn.k_proj,21.35356,0.05000,0.237
|
| 143 |
+
20,self_attn.v_proj,44.00055,0.05000,0.240
|
| 144 |
+
20,self_attn.q_proj,143.75569,0.05000,0.246
|
| 145 |
+
20,self_attn.o_proj,5.11928,0.05000,0.246
|
| 146 |
+
20,mlp.up_proj,495.64117,0.05000,0.258
|
| 147 |
+
20,mlp.gate_proj,540.19043,0.05000,0.268
|
| 148 |
+
20,mlp.down_proj,19.63391,0.05000,1.315
|
| 149 |
+
21,self_attn.k_proj,23.84112,0.05000,0.238
|
| 150 |
+
21,self_attn.v_proj,72.92213,0.05000,0.239
|
| 151 |
+
21,self_attn.q_proj,177.69803,0.05000,0.242
|
| 152 |
+
21,self_attn.o_proj,12.85544,0.05000,0.241
|
| 153 |
+
21,mlp.up_proj,554.14130,0.05000,0.257
|
| 154 |
+
21,mlp.gate_proj,570.48572,0.05000,0.268
|
| 155 |
+
21,mlp.down_proj,196.02072,0.05000,1.320
|
| 156 |
+
22,self_attn.k_proj,22.17667,0.05000,0.237
|
| 157 |
+
22,self_attn.v_proj,66.65771,0.05000,0.239
|
| 158 |
+
22,self_attn.q_proj,167.72662,0.05000,0.245
|
| 159 |
+
22,self_attn.o_proj,2.24238,0.05000,0.242
|
| 160 |
+
22,mlp.up_proj,406.67615,0.05000,0.259
|
| 161 |
+
22,mlp.gate_proj,387.07877,0.05000,0.265
|
| 162 |
+
22,mlp.down_proj,31.63613,0.05000,1.329
|
| 163 |
+
23,self_attn.k_proj,27.19038,0.05000,0.237
|
| 164 |
+
23,self_attn.v_proj,55.59654,0.05000,0.240
|
| 165 |
+
23,self_attn.q_proj,218.93060,0.05000,0.243
|
| 166 |
+
23,self_attn.o_proj,13.96109,0.05000,0.238
|
| 167 |
+
23,mlp.up_proj,507.27164,0.05000,0.255
|
| 168 |
+
23,mlp.gate_proj,520.63934,0.05000,0.262
|
| 169 |
+
23,mlp.down_proj,124.49292,0.05000,1.328
|
quant_log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
[{"layer": 0, "module": "self_attn.k_proj", "loss": "0.92654", "damp": "0.05000", "time": "0.383", "fwd_time": "0.183"}, {"layer": 0, "module": "self_attn.v_proj", "loss": "0.01888", "damp": "0.05000", "time": "0.240", "fwd_time": "0.183"}, {"layer": 0, "module": "self_attn.q_proj", "loss": "5.94556", "damp": "0.05000", "time": "0.247", "fwd_time": "0.183"}, {"layer": 0, "module": "self_attn.o_proj", "loss": "0.00328", "damp": "0.05000", "time": "0.243", "fwd_time": "0.005"}, {"layer": 0, "module": "mlp.up_proj", "loss": "83.26855", "damp": "0.05000", "time": "0.262", "fwd_time": "0.008"}, {"layer": 0, "module": "mlp.gate_proj", "loss": "136.41730", "damp": "0.05000", "time": "0.263", "fwd_time": "0.008"}, {"layer": 0, "module": "mlp.down_proj", "loss": "1.34092", "damp": "0.05000", "time": "1.380", "fwd_time": "0.005"}, {"layer": 1, "module": "self_attn.k_proj", "loss": "8.95209", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 1, "module": "self_attn.v_proj", "loss": "0.85154", "damp": "0.05000", "time": "0.238", "fwd_time": "0.003"}, {"layer": 1, "module": "self_attn.q_proj", "loss": "31.03757", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 1, "module": "self_attn.o_proj", "loss": "0.58207", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 1, "module": "mlp.up_proj", "loss": "95.90676", "damp": "0.05000", "time": "0.259", "fwd_time": "0.003"}, {"layer": 1, "module": "mlp.gate_proj", "loss": "183.64766", "damp": "0.05000", "time": "0.261", "fwd_time": "0.003"}, {"layer": 1, "module": "mlp.down_proj", "loss": "1.14676", "damp": "0.05000", "time": "1.345", "fwd_time": "0.003"}, {"layer": 2, "module": "self_attn.k_proj", "loss": "17.36003", "damp": "0.05000", "time": "0.242", "fwd_time": "0.003"}, {"layer": 2, "module": "self_attn.v_proj", "loss": "2.11829", "damp": "0.05000", "time": "0.246", "fwd_time": "0.003"}, {"layer": 2, "module": "self_attn.q_proj", "loss": "59.42081", "damp": "0.05000", "time": "0.248", "fwd_time": "0.003"}, {"layer": 2, "module": "self_attn.o_proj", "loss": "0.41101", "damp": "0.05000", "time": "0.252", "fwd_time": "0.003"}, {"layer": 2, "module": "mlp.up_proj", "loss": "138.37152", "damp": "0.05000", "time": "0.267", "fwd_time": "0.003"}, {"layer": 2, "module": "mlp.gate_proj", "loss": "258.27576", "damp": "0.05000", "time": "0.265", "fwd_time": "0.003"}, {"layer": 2, "module": "mlp.down_proj", "loss": "87.07992", "damp": "0.05000", "time": "1.390", "fwd_time": "0.003"}, {"layer": 3, "module": "self_attn.k_proj", "loss": "21.04375", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 3, "module": "self_attn.v_proj", "loss": "4.92936", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 3, "module": "self_attn.q_proj", "loss": "83.55756", "damp": "0.05000", "time": "0.250", "fwd_time": "0.003"}, {"layer": 3, "module": "self_attn.o_proj", "loss": "0.64188", "damp": "0.05000", "time": "0.250", "fwd_time": "0.003"}, {"layer": 3, "module": "mlp.up_proj", "loss": "334.65601", "damp": "0.05000", "time": "0.267", "fwd_time": "0.003"}, {"layer": 3, "module": "mlp.gate_proj", "loss": "592.50232", "damp": "0.05000", "time": "0.276", "fwd_time": "0.003"}, {"layer": 3, "module": "mlp.down_proj", "loss": "152.53775", "damp": "0.05000", "time": "1.373", "fwd_time": "0.003"}, {"layer": 4, "module": "self_attn.k_proj", "loss": "12.77439", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 4, "module": "self_attn.v_proj", "loss": "5.69861", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 4, "module": "self_attn.q_proj", "loss": "61.66964", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 4, "module": "self_attn.o_proj", "loss": "1.54178", "damp": "0.05000", "time": "0.243", "fwd_time": "0.003"}, {"layer": 4, "module": "mlp.up_proj", "loss": "202.40878", "damp": "0.05000", "time": "0.260", "fwd_time": "0.003"}, {"layer": 4, "module": "mlp.gate_proj", "loss": "317.82367", "damp": "0.05000", "time": "0.263", "fwd_time": "0.003"}, {"layer": 4, "module": "mlp.down_proj", "loss": "2.41736", "damp": "0.05000", "time": "1.319", "fwd_time": "0.004"}, {"layer": 5, "module": "self_attn.k_proj", "loss": "14.18274", "damp": "0.05000", "time": "0.238", "fwd_time": "0.003"}, {"layer": 5, "module": "self_attn.v_proj", "loss": "6.86500", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 5, "module": "self_attn.q_proj", "loss": "69.48232", "damp": "0.05000", "time": "0.253", "fwd_time": "0.003"}, {"layer": 5, "module": "self_attn.o_proj", "loss": "0.91597", "damp": "0.05000", "time": "0.254", "fwd_time": "0.003"}, {"layer": 5, "module": "mlp.up_proj", "loss": "250.59880", "damp": "0.05000", "time": "0.259", "fwd_time": "0.003"}, {"layer": 5, "module": "mlp.gate_proj", "loss": "503.84485", "damp": "0.05000", "time": "0.279", "fwd_time": "0.003"}, {"layer": 5, "module": "mlp.down_proj", "loss": "2.38952", "damp": "0.05000", "time": "1.385", "fwd_time": "0.004"}, {"layer": 6, "module": "self_attn.k_proj", "loss": "13.24366", "damp": "0.05000", "time": "0.249", "fwd_time": "0.003"}, {"layer": 6, "module": "self_attn.v_proj", "loss": "3.92612", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 6, "module": "self_attn.q_proj", "loss": "57.82330", "damp": "0.05000", "time": "0.256", "fwd_time": "0.003"}, {"layer": 6, "module": "self_attn.o_proj", "loss": "0.82199", "damp": "0.05000", "time": "0.248", "fwd_time": "0.003"}, {"layer": 6, "module": "mlp.up_proj", "loss": "202.01077", "damp": "0.05000", "time": "0.260", "fwd_time": "0.003"}, {"layer": 6, "module": "mlp.gate_proj", "loss": "291.08887", "damp": "0.05000", "time": "0.263", "fwd_time": "0.003"}, {"layer": 6, "module": "mlp.down_proj", "loss": "2.34200", "damp": "0.05000", "time": "1.317", "fwd_time": "0.003"}, {"layer": 7, "module": "self_attn.k_proj", "loss": "20.47707", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 7, "module": "self_attn.v_proj", "loss": "6.82208", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 7, "module": "self_attn.q_proj", "loss": "83.89909", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 7, "module": "self_attn.o_proj", "loss": "1.38920", "damp": "0.05000", "time": "0.239", "fwd_time": "0.004"}, {"layer": 7, "module": "mlp.up_proj", "loss": "215.59988", "damp": "0.05000", "time": "0.260", "fwd_time": "0.003"}, {"layer": 7, "module": "mlp.gate_proj", "loss": "279.67908", "damp": "0.05000", "time": "0.263", "fwd_time": "0.003"}, {"layer": 7, "module": "mlp.down_proj", "loss": "2.72322", "damp": "0.05000", "time": "1.318", "fwd_time": "0.003"}, {"layer": 8, "module": "self_attn.k_proj", "loss": "15.35229", "damp": "0.05000", "time": "0.240", "fwd_time": "0.008"}, {"layer": 8, "module": "self_attn.v_proj", "loss": "5.31779", "damp": "0.05000", "time": "0.242", "fwd_time": "0.008"}, {"layer": 8, "module": "self_attn.q_proj", "loss": "72.20273", "damp": "0.05000", "time": "0.243", "fwd_time": "0.008"}, {"layer": 8, "module": "self_attn.o_proj", "loss": "2.27721", "damp": "0.05000", "time": "0.250", "fwd_time": "0.003"}, {"layer": 8, "module": "mlp.up_proj", "loss": "190.38971", "damp": "0.05000", "time": "0.262", "fwd_time": "0.003"}, {"layer": 8, "module": "mlp.gate_proj", "loss": "251.40579", "damp": "0.05000", "time": "0.269", "fwd_time": "0.003"}, {"layer": 8, "module": "mlp.down_proj", "loss": "1.84644", "damp": "0.05000", "time": "1.402", "fwd_time": "0.003"}, {"layer": 9, "module": "self_attn.k_proj", "loss": "46.89391", "damp": "0.05000", "time": "0.242", "fwd_time": "0.003"}, {"layer": 9, "module": "self_attn.v_proj", "loss": "12.24958", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 9, "module": "self_attn.q_proj", "loss": "185.18671", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 9, "module": "self_attn.o_proj", "loss": "1.13563", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 9, "module": "mlp.up_proj", "loss": "186.08925", "damp": "0.05000", "time": "0.258", "fwd_time": "0.003"}, {"layer": 9, "module": "mlp.gate_proj", "loss": "219.94760", "damp": "0.05000", "time": "0.280", "fwd_time": "0.003"}, {"layer": 9, "module": "mlp.down_proj", "loss": "1.89974", "damp": "0.05000", "time": "1.314", "fwd_time": "0.003"}, {"layer": 10, "module": "self_attn.k_proj", "loss": "12.25381", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 10, "module": "self_attn.v_proj", "loss": "8.53600", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 10, "module": "self_attn.q_proj", "loss": "61.72304", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 10, "module": "self_attn.o_proj", "loss": "2.15923", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 10, "module": "mlp.up_proj", "loss": "153.92357", "damp": "0.05000", "time": "0.263", "fwd_time": "0.003"}, {"layer": 10, "module": "mlp.gate_proj", "loss": "200.48236", "damp": "0.05000", "time": "0.261", "fwd_time": "0.003"}, {"layer": 10, "module": "mlp.down_proj", "loss": "1.46866", "damp": "0.05000", "time": "1.325", "fwd_time": "0.004"}, {"layer": 11, "module": "self_attn.k_proj", "loss": "47.32881", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 11, "module": "self_attn.v_proj", "loss": "12.32052", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 11, "module": "self_attn.q_proj", "loss": "172.02649", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 11, "module": "self_attn.o_proj", "loss": "0.99634", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 11, "module": "mlp.up_proj", "loss": "166.91438", "damp": "0.05000", "time": "0.258", "fwd_time": "0.003"}, {"layer": 11, "module": "mlp.gate_proj", "loss": "183.99411", "damp": "0.05000", "time": "0.271", "fwd_time": "0.003"}, {"layer": 11, "module": "mlp.down_proj", "loss": "2.20383", "damp": "0.05000", "time": "1.308", "fwd_time": "0.003"}, {"layer": 12, "module": "self_attn.k_proj", "loss": "10.70629", "damp": "0.05000", "time": "0.234", "fwd_time": "0.003"}, {"layer": 12, "module": "self_attn.v_proj", "loss": "6.82535", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 12, "module": "self_attn.q_proj", "loss": "58.90049", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 12, "module": "self_attn.o_proj", "loss": "2.06957", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 12, "module": "mlp.up_proj", "loss": "151.14467", "damp": "0.05000", "time": "0.259", "fwd_time": "0.004"}, {"layer": 12, "module": "mlp.gate_proj", "loss": "168.46320", "damp": "0.05000", "time": "0.273", "fwd_time": "0.004"}, {"layer": 12, "module": "mlp.down_proj", "loss": "1.57911", "damp": "0.05000", "time": "1.320", "fwd_time": "0.004"}, {"layer": 13, "module": "self_attn.k_proj", "loss": "20.42959", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 13, "module": "self_attn.v_proj", "loss": "8.33975", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 13, "module": "self_attn.q_proj", "loss": "100.85551", "damp": "0.05000", "time": "0.243", "fwd_time": "0.003"}, {"layer": 13, "module": "self_attn.o_proj", "loss": "1.29940", "damp": "0.05000", "time": "0.243", "fwd_time": "0.003"}, {"layer": 13, "module": "mlp.up_proj", "loss": "167.68123", "damp": "0.05000", "time": "0.257", "fwd_time": "0.003"}, {"layer": 13, "module": "mlp.gate_proj", "loss": "170.36960", "damp": "0.05000", "time": "0.267", "fwd_time": "0.003"}, {"layer": 13, "module": "mlp.down_proj", "loss": "1.88119", "damp": "0.05000", "time": "1.320", "fwd_time": "0.004"}, {"layer": 14, "module": "self_attn.k_proj", "loss": "12.73074", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 14, "module": "self_attn.v_proj", "loss": "11.76164", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 14, "module": "self_attn.q_proj", "loss": "77.89767", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 14, "module": "self_attn.o_proj", "loss": "3.52199", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 14, "module": "mlp.up_proj", "loss": "163.05870", "damp": "0.05000", "time": "0.254", "fwd_time": "0.003"}, {"layer": 14, "module": "mlp.gate_proj", "loss": "184.55475", "damp": "0.05000", "time": "0.260", "fwd_time": "0.003"}, {"layer": 14, "module": "mlp.down_proj", "loss": "2.35992", "damp": "0.05000", "time": "1.309", "fwd_time": "0.004"}, {"layer": 15, "module": "self_attn.k_proj", "loss": "13.67384", "damp": "0.05000", "time": "0.233", "fwd_time": "0.003"}, {"layer": 15, "module": "self_attn.v_proj", "loss": "9.17948", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 15, "module": "self_attn.q_proj", "loss": "67.20424", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 15, "module": "self_attn.o_proj", "loss": "2.04910", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 15, "module": "mlp.up_proj", "loss": "210.13235", "damp": "0.05000", "time": "0.274", "fwd_time": "0.003"}, {"layer": 15, "module": "mlp.gate_proj", "loss": "220.19116", "damp": "0.05000", "time": "0.269", "fwd_time": "0.003"}, {"layer": 15, "module": "mlp.down_proj", "loss": "3.57103", "damp": "0.05000", "time": "1.396", "fwd_time": "0.003"}, {"layer": 16, "module": "self_attn.k_proj", "loss": "29.70275", "damp": "0.05000", "time": "0.244", "fwd_time": "0.003"}, {"layer": 16, "module": "self_attn.v_proj", "loss": "24.40463", "damp": "0.05000", "time": "0.251", "fwd_time": "0.003"}, {"layer": 16, "module": "self_attn.q_proj", "loss": "166.54938", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 16, "module": "self_attn.o_proj", "loss": "1.16431", "damp": "0.05000", "time": "0.251", "fwd_time": "0.003"}, {"layer": 16, "module": "mlp.up_proj", "loss": "267.70422", "damp": "0.05000", "time": "0.272", "fwd_time": "0.005"}, {"layer": 16, "module": "mlp.gate_proj", "loss": "344.47858", "damp": "0.05000", "time": "0.266", "fwd_time": "0.005"}, {"layer": 16, "module": "mlp.down_proj", "loss": "7.87296", "damp": "0.05000", "time": "1.311", "fwd_time": "0.003"}, {"layer": 17, "module": "self_attn.k_proj", "loss": "15.50768", "damp": "0.05000", "time": "0.233", "fwd_time": "0.003"}, {"layer": 17, "module": "self_attn.v_proj", "loss": "14.58982", "damp": "0.05000", "time": "0.236", "fwd_time": "0.003"}, {"layer": 17, "module": "self_attn.q_proj", "loss": "101.04700", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 17, "module": "self_attn.o_proj", "loss": "1.79011", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 17, "module": "mlp.up_proj", "loss": "316.87897", "damp": "0.05000", "time": "0.268", "fwd_time": "0.003"}, {"layer": 17, "module": "mlp.gate_proj", "loss": "487.06854", "damp": "0.05000", "time": "0.274", "fwd_time": "0.003"}, {"layer": 17, "module": "mlp.down_proj", "loss": "5.82991", "damp": "0.05000", "time": "1.393", "fwd_time": "0.004"}, {"layer": 18, "module": "self_attn.k_proj", "loss": "16.92690", "damp": "0.05000", "time": "0.250", "fwd_time": "0.003"}, {"layer": 18, "module": "self_attn.v_proj", "loss": "14.79226", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 18, "module": "self_attn.q_proj", "loss": "90.39028", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 18, "module": "self_attn.o_proj", "loss": "2.17428", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 18, "module": "mlp.up_proj", "loss": "308.24667", "damp": "0.05000", "time": "0.257", "fwd_time": "0.003"}, {"layer": 18, "module": "mlp.gate_proj", "loss": "386.23010", "damp": "0.05000", "time": "0.265", "fwd_time": "0.003"}, {"layer": 18, "module": "mlp.down_proj", "loss": "5.66360", "damp": "0.05000", "time": "1.328", "fwd_time": "0.003"}, {"layer": 19, "module": "self_attn.k_proj", "loss": "15.91953", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 19, "module": "self_attn.v_proj", "loss": "15.05818", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 19, "module": "self_attn.q_proj", "loss": "97.57352", "damp": "0.05000", "time": "0.242", "fwd_time": "0.003"}, {"layer": 19, "module": "self_attn.o_proj", "loss": "2.65458", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 19, "module": "mlp.up_proj", "loss": "457.87988", "damp": "0.05000", "time": "0.259", "fwd_time": "0.003"}, {"layer": 19, "module": "mlp.gate_proj", "loss": "545.14697", "damp": "0.05000", "time": "0.265", "fwd_time": "0.003"}, {"layer": 19, "module": "mlp.down_proj", "loss": "13.83433", "damp": "0.05000", "time": "1.321", "fwd_time": "0.003"}, {"layer": 20, "module": "self_attn.k_proj", "loss": "21.35356", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 20, "module": "self_attn.v_proj", "loss": "44.00055", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 20, "module": "self_attn.q_proj", "loss": "143.75569", "damp": "0.05000", "time": "0.246", "fwd_time": "0.003"}, {"layer": 20, "module": "self_attn.o_proj", "loss": "5.11928", "damp": "0.05000", "time": "0.246", "fwd_time": "0.003"}, {"layer": 20, "module": "mlp.up_proj", "loss": "495.64117", "damp": "0.05000", "time": "0.258", "fwd_time": "0.003"}, {"layer": 20, "module": "mlp.gate_proj", "loss": "540.19043", "damp": "0.05000", "time": "0.268", "fwd_time": "0.003"}, {"layer": 20, "module": "mlp.down_proj", "loss": "19.63391", "damp": "0.05000", "time": "1.315", "fwd_time": "0.004"}, {"layer": 21, "module": "self_attn.k_proj", "loss": "23.84112", "damp": "0.05000", "time": "0.238", "fwd_time": "0.003"}, {"layer": 21, "module": "self_attn.v_proj", "loss": "72.92213", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 21, "module": "self_attn.q_proj", "loss": "177.69803", "damp": "0.05000", "time": "0.242", "fwd_time": "0.003"}, {"layer": 21, "module": "self_attn.o_proj", "loss": "12.85544", "damp": "0.05000", "time": "0.241", "fwd_time": "0.003"}, {"layer": 21, "module": "mlp.up_proj", "loss": "554.14130", "damp": "0.05000", "time": "0.257", "fwd_time": "0.003"}, {"layer": 21, "module": "mlp.gate_proj", "loss": "570.48572", "damp": "0.05000", "time": "0.268", "fwd_time": "0.003"}, {"layer": 21, "module": "mlp.down_proj", "loss": "196.02072", "damp": "0.05000", "time": "1.320", "fwd_time": "0.004"}, {"layer": 22, "module": "self_attn.k_proj", "loss": "22.17667", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 22, "module": "self_attn.v_proj", "loss": "66.65771", "damp": "0.05000", "time": "0.239", "fwd_time": "0.003"}, {"layer": 22, "module": "self_attn.q_proj", "loss": "167.72662", "damp": "0.05000", "time": "0.245", "fwd_time": "0.003"}, {"layer": 22, "module": "self_attn.o_proj", "loss": "2.24238", "damp": "0.05000", "time": "0.242", "fwd_time": "0.003"}, {"layer": 22, "module": "mlp.up_proj", "loss": "406.67615", "damp": "0.05000", "time": "0.259", "fwd_time": "0.003"}, {"layer": 22, "module": "mlp.gate_proj", "loss": "387.07877", "damp": "0.05000", "time": "0.265", "fwd_time": "0.003"}, {"layer": 22, "module": "mlp.down_proj", "loss": "31.63613", "damp": "0.05000", "time": "1.329", "fwd_time": "0.003"}, {"layer": 23, "module": "self_attn.k_proj", "loss": "27.19038", "damp": "0.05000", "time": "0.237", "fwd_time": "0.003"}, {"layer": 23, "module": "self_attn.v_proj", "loss": "55.59654", "damp": "0.05000", "time": "0.240", "fwd_time": "0.003"}, {"layer": 23, "module": "self_attn.q_proj", "loss": "218.93060", "damp": "0.05000", "time": "0.243", "fwd_time": "0.003"}, {"layer": 23, "module": "self_attn.o_proj", "loss": "13.96109", "damp": "0.05000", "time": "0.238", "fwd_time": "0.003"}, {"layer": 23, "module": "mlp.up_proj", "loss": "507.27164", "damp": "0.05000", "time": "0.255", "fwd_time": "0.003"}, {"layer": 23, "module": "mlp.gate_proj", "loss": "520.63934", "damp": "0.05000", "time": "0.262", "fwd_time": "0.003"}, {"layer": 23, "module": "mlp.down_proj", "loss": "124.49292", "damp": "0.05000", "time": "1.328", "fwd_time": "0.003"}]
|
quantize_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"dynamic": null,
|
| 4 |
+
"group_size": 32,
|
| 5 |
+
"desc_act": false,
|
| 6 |
+
"sym": true,
|
| 7 |
+
"lm_head": false,
|
| 8 |
+
"quant_method": "gptq",
|
| 9 |
+
"checkpoint_format": "gptq",
|
| 10 |
+
"pack_dtype": "int32",
|
| 11 |
+
"meta": {
|
| 12 |
+
"quantizer": [
|
| 13 |
+
"gptqmodel:1.8.0-dev"
|
| 14 |
+
],
|
| 15 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 16 |
+
"damp_percent": 0.05,
|
| 17 |
+
"damp_auto_increment": 0.0025,
|
| 18 |
+
"static_groups": false,
|
| 19 |
+
"true_sequential": true,
|
| 20 |
+
"mse": 0.0
|
| 21 |
+
}
|
| 22 |
+
}
|
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) 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{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<unk>",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 207 |
+
"unk_token": null,
|
| 208 |
+
"_commit_hash": null
|
| 209 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|