初始化项目,由ModelHub XC社区提供模型
Model: shisa-ai/Mistral-Nemo-Japanese-Instruct-2408-GPTQ-W4A16-gs32 Source: Original Platform
This commit is contained in:
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
12
README.md
Normal file
12
README.md
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- ja
|
||||||
|
- en
|
||||||
|
base_model:
|
||||||
|
- cyberagent/Mistral-Nemo-Japanese-Instruct-2408
|
||||||
|
tags:
|
||||||
|
- gptq
|
||||||
|
---
|
||||||
|
|
||||||
|
W4A16 gs32 GPTQ quant of [cyberagent/Mistral-Nemo-Japanese-Instruct-2408](https://huggingface.co/cyberagent/Mistral-Nemo-Japanese-Instruct-2408) w/ [GPTQModel](https://github.com/ModelCloud/GPTQModel) 1.7.2 using [augmxnt/ultra-orca-boros-en-ja-v1](https://huggingface.co/datasets/augmxnt/ultra-orca-boros-en-ja-v1) as calibration set
|
||||||
50
config.json
Normal file
50
config.json
Normal file
@@ -0,0 +1,50 @@
|
|||||||
|
{
|
||||||
|
"_attn_implementation_autoset": true,
|
||||||
|
"_name_or_path": "/fsx/ubuntu/.cache/huggingface/hub/models--cyberagent--Mistral-Nemo-Japanese-Instruct-2408/snapshots/8591f78522a5d651209fc9f354c848508db7a3eb",
|
||||||
|
"architectures": [
|
||||||
|
"MistralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 131072,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 1024000,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 10,
|
||||||
|
"quantization_config": {
|
||||||
|
"bits": 4,
|
||||||
|
"checkpoint_format": "gptq",
|
||||||
|
"desc_act": true,
|
||||||
|
"dynamic": null,
|
||||||
|
"group_size": 32,
|
||||||
|
"lm_head": false,
|
||||||
|
"meta": {
|
||||||
|
"damp_auto_increment": 0.0025,
|
||||||
|
"damp_percent": 0.01,
|
||||||
|
"mse": 0.0,
|
||||||
|
"quantizer": [
|
||||||
|
"gptqmodel:1.7.0"
|
||||||
|
],
|
||||||
|
"static_groups": false,
|
||||||
|
"true_sequential": true,
|
||||||
|
"uri": "https://github.com/modelcloud/gptqmodel"
|
||||||
|
},
|
||||||
|
"quant_method": "gptq",
|
||||||
|
"sym": true
|
||||||
|
},
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.48.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 131074
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c2b1d20803f0cf850a9f43a30ddba3dc8940d8a8283ae7b5a4b66d1b57ad0e4b
|
||||||
|
size 8996969392
|
||||||
281
quant_log.csv
Normal file
281
quant_log.csv
Normal file
@@ -0,0 +1,281 @@
|
|||||||
|
layer,module,loss,damp,time
|
||||||
|
0,self_attn.k_proj,0.35479,0.01000,2.349
|
||||||
|
0,self_attn.v_proj,0.00268,0.01000,1.606
|
||||||
|
0,self_attn.q_proj,0.82359,0.01000,1.709
|
||||||
|
0,self_attn.o_proj,0.00026,0.01000,1.405
|
||||||
|
0,mlp.up_proj,0.22933,0.01000,1.936
|
||||||
|
0,mlp.gate_proj,0.24757,0.01000,1.914
|
||||||
|
0,mlp.down_proj,1.37315,0.01000,4.905
|
||||||
|
1,self_attn.k_proj,0.54634,0.01000,1.653
|
||||||
|
1,self_attn.v_proj,0.06669,0.01000,1.636
|
||||||
|
1,self_attn.q_proj,1.12471,0.01000,1.694
|
||||||
|
1,self_attn.o_proj,0.00130,0.01000,1.373
|
||||||
|
1,mlp.up_proj,0.49362,0.01000,1.993
|
||||||
|
1,mlp.gate_proj,0.55734,0.01000,1.956
|
||||||
|
1,mlp.down_proj,0.00385,0.01000,5.071
|
||||||
|
2,self_attn.k_proj,0.42915,0.01000,1.694
|
||||||
|
2,self_attn.v_proj,0.07932,0.01000,1.647
|
||||||
|
2,self_attn.q_proj,0.94002,0.01000,1.693
|
||||||
|
2,self_attn.o_proj,0.00277,0.01000,1.394
|
||||||
|
2,mlp.up_proj,1.05308,0.01000,1.929
|
||||||
|
2,mlp.gate_proj,1.28850,0.01000,1.936
|
||||||
|
2,mlp.down_proj,0.06975,0.01000,4.864
|
||||||
|
3,self_attn.k_proj,0.92321,0.01000,1.623
|
||||||
|
3,self_attn.v_proj,0.14390,0.01000,1.649
|
||||||
|
3,self_attn.q_proj,2.24338,0.01000,1.682
|
||||||
|
3,self_attn.o_proj,0.00383,0.01000,1.375
|
||||||
|
3,mlp.up_proj,1.38623,0.01000,1.932
|
||||||
|
3,mlp.gate_proj,1.75863,0.01000,1.927
|
||||||
|
3,mlp.down_proj,0.01949,0.01000,4.850
|
||||||
|
4,self_attn.k_proj,0.70682,0.01000,1.651
|
||||||
|
4,self_attn.v_proj,0.17194,0.01000,1.583
|
||||||
|
4,self_attn.q_proj,1.66714,0.01000,1.630
|
||||||
|
4,self_attn.o_proj,0.00794,0.01000,1.341
|
||||||
|
4,mlp.up_proj,1.81410,0.01000,1.903
|
||||||
|
4,mlp.gate_proj,2.39854,0.01000,1.895
|
||||||
|
4,mlp.down_proj,0.03273,0.01000,4.847
|
||||||
|
5,self_attn.k_proj,0.92816,0.01000,1.608
|
||||||
|
5,self_attn.v_proj,0.18893,0.01000,1.555
|
||||||
|
5,self_attn.q_proj,2.33771,0.01000,1.629
|
||||||
|
5,self_attn.o_proj,0.00867,0.01000,1.318
|
||||||
|
5,mlp.up_proj,2.42875,0.01000,1.920
|
||||||
|
5,mlp.gate_proj,3.08451,0.01000,1.864
|
||||||
|
5,mlp.down_proj,0.04925,0.01000,4.845
|
||||||
|
6,self_attn.k_proj,1.07199,0.01000,1.631
|
||||||
|
6,self_attn.v_proj,0.18683,0.01000,1.573
|
||||||
|
6,self_attn.q_proj,2.46528,0.01000,1.628
|
||||||
|
6,self_attn.o_proj,0.01993,0.01000,1.387
|
||||||
|
6,mlp.up_proj,2.95284,0.01000,1.893
|
||||||
|
6,mlp.gate_proj,3.81204,0.01000,1.895
|
||||||
|
6,mlp.down_proj,0.07002,0.01000,4.853
|
||||||
|
7,self_attn.k_proj,1.08823,0.01000,1.636
|
||||||
|
7,self_attn.v_proj,0.28548,0.01000,1.569
|
||||||
|
7,self_attn.q_proj,2.76811,0.01000,1.654
|
||||||
|
7,self_attn.o_proj,0.03065,0.01000,1.345
|
||||||
|
7,mlp.up_proj,3.46371,0.01000,1.912
|
||||||
|
7,mlp.gate_proj,4.24435,0.01000,1.898
|
||||||
|
7,mlp.down_proj,0.08456,0.01000,4.945
|
||||||
|
8,self_attn.k_proj,1.16355,0.01000,1.617
|
||||||
|
8,self_attn.v_proj,0.28823,0.01000,1.582
|
||||||
|
8,self_attn.q_proj,2.91725,0.01000,1.675
|
||||||
|
8,self_attn.o_proj,0.03290,0.01000,1.433
|
||||||
|
8,mlp.up_proj,3.98309,0.01000,1.948
|
||||||
|
8,mlp.gate_proj,4.53147,0.01000,1.949
|
||||||
|
8,mlp.down_proj,0.10271,0.01000,5.016
|
||||||
|
9,self_attn.k_proj,1.29539,0.01000,1.722
|
||||||
|
9,self_attn.v_proj,0.42527,0.01000,1.761
|
||||||
|
9,self_attn.q_proj,3.25226,0.01000,1.695
|
||||||
|
9,self_attn.o_proj,0.05341,0.01000,1.411
|
||||||
|
9,mlp.up_proj,4.35932,0.01000,1.961
|
||||||
|
9,mlp.gate_proj,4.64491,0.01000,1.944
|
||||||
|
9,mlp.down_proj,0.12074,0.01000,4.965
|
||||||
|
10,self_attn.k_proj,1.25597,0.01000,1.706
|
||||||
|
10,self_attn.v_proj,0.39587,0.01000,1.630
|
||||||
|
10,self_attn.q_proj,3.27324,0.01000,1.729
|
||||||
|
10,self_attn.o_proj,0.06494,0.01000,1.398
|
||||||
|
10,mlp.up_proj,4.79890,0.01000,1.981
|
||||||
|
10,mlp.gate_proj,4.91185,0.01000,1.929
|
||||||
|
10,mlp.down_proj,0.13928,0.01000,5.106
|
||||||
|
11,self_attn.k_proj,1.56255,0.01000,1.750
|
||||||
|
11,self_attn.v_proj,0.44044,0.01000,1.676
|
||||||
|
11,self_attn.q_proj,3.97072,0.01000,1.734
|
||||||
|
11,self_attn.o_proj,0.07647,0.01000,1.422
|
||||||
|
11,mlp.up_proj,5.44356,0.01000,1.984
|
||||||
|
11,mlp.gate_proj,6.01119,0.01000,1.976
|
||||||
|
11,mlp.down_proj,0.15027,0.01000,5.132
|
||||||
|
12,self_attn.k_proj,1.50076,0.01000,1.713
|
||||||
|
12,self_attn.v_proj,0.55479,0.01000,1.642
|
||||||
|
12,self_attn.q_proj,3.89300,0.01000,1.739
|
||||||
|
12,self_attn.o_proj,0.07701,0.01000,1.434
|
||||||
|
12,mlp.up_proj,6.02853,0.01000,2.002
|
||||||
|
12,mlp.gate_proj,6.57857,0.01000,1.959
|
||||||
|
12,mlp.down_proj,0.16847,0.01000,5.181
|
||||||
|
13,self_attn.k_proj,1.90422,0.01000,1.729
|
||||||
|
13,self_attn.v_proj,0.58111,0.01000,1.654
|
||||||
|
13,self_attn.q_proj,4.91283,0.01000,1.749
|
||||||
|
13,self_attn.o_proj,0.09638,0.01000,1.414
|
||||||
|
13,mlp.up_proj,6.54751,0.01000,1.982
|
||||||
|
13,mlp.gate_proj,6.87143,0.01000,1.996
|
||||||
|
13,mlp.down_proj,0.21942,0.01000,5.136
|
||||||
|
14,self_attn.k_proj,2.09946,0.01000,1.731
|
||||||
|
14,self_attn.v_proj,0.65708,0.01000,1.623
|
||||||
|
14,self_attn.q_proj,5.52672,0.01000,1.734
|
||||||
|
14,self_attn.o_proj,0.08825,0.01000,1.415
|
||||||
|
14,mlp.up_proj,7.28541,0.01000,1.987
|
||||||
|
14,mlp.gate_proj,7.21690,0.01000,2.006
|
||||||
|
14,mlp.down_proj,0.22773,0.01000,5.153
|
||||||
|
15,self_attn.k_proj,1.91788,0.01000,1.722
|
||||||
|
15,self_attn.v_proj,0.63475,0.01000,1.677
|
||||||
|
15,self_attn.q_proj,4.70698,0.01000,1.727
|
||||||
|
15,self_attn.o_proj,0.10500,0.01000,1.423
|
||||||
|
15,mlp.up_proj,7.60786,0.01000,1.987
|
||||||
|
15,mlp.gate_proj,7.09275,0.01000,2.003
|
||||||
|
15,mlp.down_proj,0.26158,0.01000,5.205
|
||||||
|
16,self_attn.k_proj,1.99614,0.01000,1.711
|
||||||
|
16,self_attn.v_proj,0.73938,0.01000,1.662
|
||||||
|
16,self_attn.q_proj,4.97917,0.01000,1.740
|
||||||
|
16,self_attn.o_proj,0.13482,0.01000,1.417
|
||||||
|
16,mlp.up_proj,8.12699,0.01000,1.991
|
||||||
|
16,mlp.gate_proj,7.33698,0.01000,1.981
|
||||||
|
16,mlp.down_proj,0.31113,0.01000,5.161
|
||||||
|
17,self_attn.k_proj,1.86525,0.01000,1.723
|
||||||
|
17,self_attn.v_proj,0.90671,0.01000,1.678
|
||||||
|
17,self_attn.q_proj,5.01605,0.01000,1.680
|
||||||
|
17,self_attn.o_proj,0.17565,0.01000,1.379
|
||||||
|
17,mlp.up_proj,8.98972,0.01000,1.941
|
||||||
|
17,mlp.gate_proj,7.92179,0.01000,1.932
|
||||||
|
17,mlp.down_proj,0.38754,0.01000,4.989
|
||||||
|
18,self_attn.k_proj,2.20511,0.01000,1.657
|
||||||
|
18,self_attn.v_proj,0.90475,0.01000,1.591
|
||||||
|
18,self_attn.q_proj,5.73960,0.01000,1.678
|
||||||
|
18,self_attn.o_proj,0.23413,0.01000,1.366
|
||||||
|
18,mlp.up_proj,9.93882,0.01000,1.950
|
||||||
|
18,mlp.gate_proj,9.19216,0.01000,1.930
|
||||||
|
18,mlp.down_proj,0.46037,0.01000,4.896
|
||||||
|
19,self_attn.k_proj,2.24348,0.01000,1.629
|
||||||
|
19,self_attn.v_proj,1.30353,0.01000,1.628
|
||||||
|
19,self_attn.q_proj,6.65672,0.01000,1.692
|
||||||
|
19,self_attn.o_proj,0.17194,0.01000,1.385
|
||||||
|
19,mlp.up_proj,10.52798,0.01000,1.970
|
||||||
|
19,mlp.gate_proj,10.01086,0.01000,1.935
|
||||||
|
19,mlp.down_proj,0.50281,0.01000,5.060
|
||||||
|
20,self_attn.k_proj,2.35084,0.01000,1.742
|
||||||
|
20,self_attn.v_proj,1.16817,0.01000,1.616
|
||||||
|
20,self_attn.q_proj,6.67217,0.01000,1.681
|
||||||
|
20,self_attn.o_proj,0.15849,0.01000,1.382
|
||||||
|
20,mlp.up_proj,11.43906,0.01000,2.007
|
||||||
|
20,mlp.gate_proj,11.54784,0.01000,1.990
|
||||||
|
20,mlp.down_proj,0.56608,0.01000,5.002
|
||||||
|
21,self_attn.k_proj,2.25952,0.01000,1.673
|
||||||
|
21,self_attn.v_proj,1.03793,0.01000,1.616
|
||||||
|
21,self_attn.q_proj,6.24515,0.01000,1.695
|
||||||
|
21,self_attn.o_proj,0.13921,0.01000,1.371
|
||||||
|
21,mlp.up_proj,12.59370,0.01000,1.941
|
||||||
|
21,mlp.gate_proj,13.18203,0.01000,1.925
|
||||||
|
21,mlp.down_proj,0.65296,0.01000,4.990
|
||||||
|
22,self_attn.k_proj,2.22437,0.01000,1.709
|
||||||
|
22,self_attn.v_proj,1.47607,0.01000,1.619
|
||||||
|
22,self_attn.q_proj,6.59270,0.01000,1.687
|
||||||
|
22,self_attn.o_proj,0.17644,0.01000,1.374
|
||||||
|
22,mlp.up_proj,13.96070,0.01000,1.934
|
||||||
|
22,mlp.gate_proj,14.97387,0.01000,1.942
|
||||||
|
22,mlp.down_proj,0.82510,0.01000,5.001
|
||||||
|
23,self_attn.k_proj,2.38086,0.01000,1.676
|
||||||
|
23,self_attn.v_proj,1.46058,0.01000,1.642
|
||||||
|
23,self_attn.q_proj,6.76258,0.01000,1.692
|
||||||
|
23,self_attn.o_proj,0.17248,0.01000,1.387
|
||||||
|
23,mlp.up_proj,14.85585,0.01000,1.932
|
||||||
|
23,mlp.gate_proj,15.75251,0.01000,1.901
|
||||||
|
23,mlp.down_proj,0.95195,0.01000,4.966
|
||||||
|
24,self_attn.k_proj,2.63904,0.01000,1.661
|
||||||
|
24,self_attn.v_proj,1.58612,0.01000,1.607
|
||||||
|
24,self_attn.q_proj,7.52401,0.01000,1.681
|
||||||
|
24,self_attn.o_proj,0.23829,0.01000,1.377
|
||||||
|
24,mlp.up_proj,16.10369,0.01000,1.921
|
||||||
|
24,mlp.gate_proj,17.42771,0.01000,1.904
|
||||||
|
24,mlp.down_proj,0.99444,0.01000,4.953
|
||||||
|
25,self_attn.k_proj,2.90565,0.01000,1.666
|
||||||
|
25,self_attn.v_proj,1.69467,0.01000,1.588
|
||||||
|
25,self_attn.q_proj,8.14186,0.01000,1.673
|
||||||
|
25,self_attn.o_proj,0.16555,0.01000,1.373
|
||||||
|
25,mlp.up_proj,17.15473,0.01000,1.915
|
||||||
|
25,mlp.gate_proj,18.86563,0.01000,1.905
|
||||||
|
25,mlp.down_proj,1.09667,0.01000,4.972
|
||||||
|
26,self_attn.k_proj,2.89141,0.01000,1.663
|
||||||
|
26,self_attn.v_proj,1.96453,0.01000,1.535
|
||||||
|
26,self_attn.q_proj,8.08093,0.01000,1.618
|
||||||
|
26,self_attn.o_proj,0.18482,0.01000,1.328
|
||||||
|
26,mlp.up_proj,18.59406,0.01000,1.872
|
||||||
|
26,mlp.gate_proj,20.82703,0.01000,1.992
|
||||||
|
26,mlp.down_proj,1.17742,0.01000,4.828
|
||||||
|
27,self_attn.k_proj,3.05272,0.01000,1.609
|
||||||
|
27,self_attn.v_proj,2.29465,0.01000,1.547
|
||||||
|
27,self_attn.q_proj,8.93310,0.01000,1.618
|
||||||
|
27,self_attn.o_proj,0.14195,0.01000,1.318
|
||||||
|
27,mlp.up_proj,20.18908,0.01000,1.884
|
||||||
|
27,mlp.gate_proj,22.93357,0.01000,1.849
|
||||||
|
27,mlp.down_proj,1.29122,0.01000,4.823
|
||||||
|
28,self_attn.k_proj,3.17150,0.01000,1.604
|
||||||
|
28,self_attn.v_proj,2.32700,0.01000,1.546
|
||||||
|
28,self_attn.q_proj,8.92997,0.01000,1.621
|
||||||
|
28,self_attn.o_proj,0.27351,0.01000,1.319
|
||||||
|
28,mlp.up_proj,21.86856,0.01000,1.887
|
||||||
|
28,mlp.gate_proj,24.50107,0.01000,1.857
|
||||||
|
28,mlp.down_proj,1.48228,0.01000,4.848
|
||||||
|
29,self_attn.k_proj,3.09725,0.01000,1.607
|
||||||
|
29,self_attn.v_proj,3.17635,0.01000,1.547
|
||||||
|
29,self_attn.q_proj,9.09989,0.01000,1.616
|
||||||
|
29,self_attn.o_proj,0.37311,0.01000,1.341
|
||||||
|
29,mlp.up_proj,24.06158,0.01000,1.874
|
||||||
|
29,mlp.gate_proj,27.08915,0.01000,1.929
|
||||||
|
29,mlp.down_proj,1.66260,0.01000,5.058
|
||||||
|
30,self_attn.k_proj,3.52871,0.01000,1.690
|
||||||
|
30,self_attn.v_proj,2.85859,0.01000,1.629
|
||||||
|
30,self_attn.q_proj,9.94771,0.01000,1.708
|
||||||
|
30,self_attn.o_proj,0.23282,0.01000,1.413
|
||||||
|
30,mlp.up_proj,26.42622,0.01000,1.967
|
||||||
|
30,mlp.gate_proj,29.90111,0.01000,1.943
|
||||||
|
30,mlp.down_proj,1.96078,0.01000,5.088
|
||||||
|
31,self_attn.k_proj,3.17594,0.01000,1.723
|
||||||
|
31,self_attn.v_proj,2.83306,0.01000,1.621
|
||||||
|
31,self_attn.q_proj,9.12404,0.01000,1.697
|
||||||
|
31,self_attn.o_proj,0.36137,0.01000,1.397
|
||||||
|
31,mlp.up_proj,28.66065,0.01000,1.945
|
||||||
|
31,mlp.gate_proj,31.69213,0.01000,1.870
|
||||||
|
31,mlp.down_proj,2.30186,0.01000,4.915
|
||||||
|
32,self_attn.k_proj,3.19539,0.01000,1.673
|
||||||
|
32,self_attn.v_proj,3.98448,0.01000,1.636
|
||||||
|
32,self_attn.q_proj,9.97009,0.01000,1.714
|
||||||
|
32,self_attn.o_proj,0.34023,0.01000,1.404
|
||||||
|
32,mlp.up_proj,30.91885,0.01000,1.973
|
||||||
|
32,mlp.gate_proj,33.56028,0.01000,1.903
|
||||||
|
32,mlp.down_proj,2.74637,0.01000,4.990
|
||||||
|
33,self_attn.k_proj,3.47076,0.01000,1.670
|
||||||
|
33,self_attn.v_proj,3.22100,0.01000,1.623
|
||||||
|
33,self_attn.q_proj,10.57501,0.01000,1.701
|
||||||
|
33,self_attn.o_proj,0.47574,0.01000,1.392
|
||||||
|
33,mlp.up_proj,33.12611,0.01000,1.952
|
||||||
|
33,mlp.gate_proj,34.76408,0.01000,1.887
|
||||||
|
33,mlp.down_proj,3.54615,0.01000,5.018
|
||||||
|
34,self_attn.k_proj,3.05377,0.01000,1.673
|
||||||
|
34,self_attn.v_proj,6.53063,0.01000,1.612
|
||||||
|
34,self_attn.q_proj,10.03420,0.01000,1.736
|
||||||
|
34,self_attn.o_proj,0.97326,0.01000,1.377
|
||||||
|
34,mlp.up_proj,36.04812,0.01000,1.960
|
||||||
|
34,mlp.gate_proj,37.42268,0.01000,1.900
|
||||||
|
34,mlp.down_proj,4.00197,0.01000,5.060
|
||||||
|
35,self_attn.k_proj,3.36860,0.01000,1.674
|
||||||
|
35,self_attn.v_proj,5.95140,0.01000,1.608
|
||||||
|
35,self_attn.q_proj,10.86249,0.01000,1.679
|
||||||
|
35,self_attn.o_proj,0.65889,0.01000,1.392
|
||||||
|
35,mlp.up_proj,39.39637,0.01000,1.953
|
||||||
|
35,mlp.gate_proj,40.15826,0.01000,1.941
|
||||||
|
35,mlp.down_proj,4.86860,0.01000,5.032
|
||||||
|
36,self_attn.k_proj,3.07699,0.01000,1.678
|
||||||
|
36,self_attn.v_proj,6.95885,0.01000,1.641
|
||||||
|
36,self_attn.q_proj,10.35025,0.01000,1.687
|
||||||
|
36,self_attn.o_proj,0.92406,0.01000,1.377
|
||||||
|
36,mlp.up_proj,42.50772,0.01000,1.926
|
||||||
|
36,mlp.gate_proj,42.03286,0.01000,1.913
|
||||||
|
36,mlp.down_proj,6.17359,0.01000,4.961
|
||||||
|
37,self_attn.k_proj,2.74004,0.01000,1.705
|
||||||
|
37,self_attn.v_proj,7.82842,0.01000,1.647
|
||||||
|
37,self_attn.q_proj,10.62546,0.01000,1.710
|
||||||
|
37,self_attn.o_proj,2.19896,0.01000,1.450
|
||||||
|
37,mlp.up_proj,42.68120,0.01000,2.027
|
||||||
|
37,mlp.gate_proj,42.57842,0.01000,1.984
|
||||||
|
37,mlp.down_proj,7.93857,0.01000,5.068
|
||||||
|
38,self_attn.k_proj,3.25958,0.01000,1.681
|
||||||
|
38,self_attn.v_proj,11.66085,0.01000,1.620
|
||||||
|
38,self_attn.q_proj,11.31734,0.01000,1.676
|
||||||
|
38,self_attn.o_proj,2.05625,0.01000,1.383
|
||||||
|
38,mlp.up_proj,42.16687,0.01000,1.917
|
||||||
|
38,mlp.gate_proj,43.10248,0.01000,1.892
|
||||||
|
38,mlp.down_proj,9.73955,0.01000,4.959
|
||||||
|
39,self_attn.k_proj,2.71716,0.01000,1.660
|
||||||
|
39,self_attn.v_proj,6.01112,0.01000,1.611
|
||||||
|
39,self_attn.q_proj,9.59197,0.01000,1.676
|
||||||
|
39,self_attn.o_proj,1.59839,0.01000,1.366
|
||||||
|
39,mlp.up_proj,42.55232,0.01000,1.961
|
||||||
|
39,mlp.gate_proj,45.28327,0.01000,2.018
|
||||||
|
39,mlp.down_proj,15.42649,0.01000,4.955
|
||||||
|
21
quantize_config.json
Normal file
21
quantize_config.json
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
{
|
||||||
|
"bits": 4,
|
||||||
|
"dynamic": null,
|
||||||
|
"group_size": 32,
|
||||||
|
"desc_act": true,
|
||||||
|
"sym": true,
|
||||||
|
"lm_head": false,
|
||||||
|
"quant_method": "gptq",
|
||||||
|
"checkpoint_format": "gptq",
|
||||||
|
"meta": {
|
||||||
|
"quantizer": [
|
||||||
|
"gptqmodel:1.7.0"
|
||||||
|
],
|
||||||
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
||||||
|
"damp_percent": 0.01,
|
||||||
|
"damp_auto_increment": 0.0025,
|
||||||
|
"static_groups": false,
|
||||||
|
"true_sequential": true,
|
||||||
|
"mse": 0.0
|
||||||
|
}
|
||||||
|
}
|
||||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<pad>",
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ea88f9940a84ab7e0100bc369506a28ec8d5d821691dc47d4dd63f1bbdf105ed
|
||||||
|
size 17078669
|
||||||
8032
tokenizer_config.json
Normal file
8032
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user