Add files using upload-large-folder tool
Browse files- config.json +59 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +211 -0
- quantize_config.json +21 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +156 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 576,
|
| 12 |
+
"initializer_range": 0.041666666666666664,
|
| 13 |
+
"intermediate_size": 1536,
|
| 14 |
+
"is_llama_config": true,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 9,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
+
"num_key_value_heads": 3,
|
| 21 |
+
"pad_token_id": 2,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"bits": 8,
|
| 25 |
+
"checkpoint_format": "gptq",
|
| 26 |
+
"desc_act": true,
|
| 27 |
+
"group_size": 128,
|
| 28 |
+
"lm_head": false,
|
| 29 |
+
"meta": {
|
| 30 |
+
"damp_auto_increment": 0.0025,
|
| 31 |
+
"damp_percent": 0.01,
|
| 32 |
+
"mse": 0.0,
|
| 33 |
+
"quantizer": [
|
| 34 |
+
"gptqmodel:2.1.1-dev"
|
| 35 |
+
],
|
| 36 |
+
"static_groups": false,
|
| 37 |
+
"true_sequential": true,
|
| 38 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 39 |
+
},
|
| 40 |
+
"pack_dtype": "int32",
|
| 41 |
+
"quant_method": "gptq",
|
| 42 |
+
"sym": true
|
| 43 |
+
},
|
| 44 |
+
"rms_norm_eps": 1e-05,
|
| 45 |
+
"rope_interleaved": false,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 100000,
|
| 48 |
+
"tie_word_embeddings": true,
|
| 49 |
+
"torch_dtype": "bfloat16",
|
| 50 |
+
"transformers.js_config": {
|
| 51 |
+
"kv_cache_dtype": {
|
| 52 |
+
"fp16": "float16",
|
| 53 |
+
"q4f16": "float16"
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"transformers_version": "4.50.1",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49152
|
| 59 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.50.1"
|
| 7 |
+
}
|
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 sha256:5dccb798fbedd0213d8661ad75fd8693cbe6acb2a04711a1c99a4a2934dd0b07
|
| 3 |
+
size 166253936
|
quant_log.csv
ADDED
|
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.k_proj,0.00022096,0.01000,1.099
|
| 3 |
+
0,self_attn.v_proj,0.00000229,0.01000,2.435
|
| 4 |
+
0,self_attn.q_proj,0.00036210,0.01000,2.448
|
| 5 |
+
0,self_attn.o_proj,0.00000175,0.01000,2.415
|
| 6 |
+
0,mlp.up_proj,0.00150737,0.01000,1.416
|
| 7 |
+
0,mlp.gate_proj,0.00142441,0.01000,0.274
|
| 8 |
+
0,mlp.down_proj,0.00595958,0.01000,0.739
|
| 9 |
+
1,self_attn.k_proj,0.00078274,0.01000,0.286
|
| 10 |
+
1,self_attn.v_proj,0.00015115,0.01000,0.272
|
| 11 |
+
1,self_attn.q_proj,0.00174118,0.01000,0.162
|
| 12 |
+
1,self_attn.o_proj,0.00103411,0.01000,0.769
|
| 13 |
+
1,mlp.up_proj,0.00179594,0.01000,1.660
|
| 14 |
+
1,mlp.gate_proj,0.00228291,0.01000,0.973
|
| 15 |
+
1,mlp.down_proj,0.00224895,0.01000,0.746
|
| 16 |
+
2,self_attn.k_proj,0.00125878,0.01000,0.437
|
| 17 |
+
2,self_attn.v_proj,0.00020735,0.01000,0.269
|
| 18 |
+
2,self_attn.q_proj,0.00295782,0.01000,0.638
|
| 19 |
+
2,self_attn.o_proj,0.00098028,0.01000,0.810
|
| 20 |
+
2,mlp.up_proj,0.00240148,0.01000,0.318
|
| 21 |
+
2,mlp.gate_proj,0.00286920,0.01000,0.260
|
| 22 |
+
2,mlp.down_proj,0.00500130,0.01000,6.505
|
| 23 |
+
3,self_attn.k_proj,0.00188067,0.01000,1.197
|
| 24 |
+
3,self_attn.v_proj,0.00074529,0.01000,0.289
|
| 25 |
+
3,self_attn.q_proj,0.00454102,0.01000,0.292
|
| 26 |
+
3,self_attn.o_proj,0.00114469,0.01000,0.283
|
| 27 |
+
3,mlp.up_proj,0.00272536,0.01000,0.309
|
| 28 |
+
3,mlp.gate_proj,0.00309045,0.01000,0.279
|
| 29 |
+
3,mlp.down_proj,0.00337280,0.01000,0.736
|
| 30 |
+
4,self_attn.k_proj,0.00178011,0.01000,0.471
|
| 31 |
+
4,self_attn.v_proj,0.00069859,0.01000,0.149
|
| 32 |
+
4,self_attn.q_proj,0.00427734,0.01000,0.145
|
| 33 |
+
4,self_attn.o_proj,0.00194755,0.01000,1.499
|
| 34 |
+
4,mlp.up_proj,0.00357304,0.01000,0.308
|
| 35 |
+
4,mlp.gate_proj,0.00408032,0.01000,0.289
|
| 36 |
+
4,mlp.down_proj,0.00474062,0.01000,0.744
|
| 37 |
+
5,self_attn.k_proj,0.00194141,0.01000,0.269
|
| 38 |
+
5,self_attn.v_proj,0.00072606,0.01000,0.919
|
| 39 |
+
5,self_attn.q_proj,0.00453751,0.01000,1.476
|
| 40 |
+
5,self_attn.o_proj,0.00234540,0.01000,0.281
|
| 41 |
+
5,mlp.up_proj,0.00409303,0.01000,0.266
|
| 42 |
+
5,mlp.gate_proj,0.00449629,0.01000,0.596
|
| 43 |
+
5,mlp.down_proj,0.00556781,0.01000,6.516
|
| 44 |
+
6,self_attn.k_proj,0.00163071,0.01000,0.275
|
| 45 |
+
6,self_attn.v_proj,0.00068974,0.01000,0.287
|
| 46 |
+
6,self_attn.q_proj,0.00406556,0.01000,0.276
|
| 47 |
+
6,self_attn.o_proj,0.00182722,0.01000,0.284
|
| 48 |
+
6,mlp.up_proj,0.00438432,0.01000,0.273
|
| 49 |
+
6,mlp.gate_proj,0.00448065,0.01000,0.271
|
| 50 |
+
6,mlp.down_proj,0.00687783,0.01000,0.819
|
| 51 |
+
7,self_attn.k_proj,0.00229149,0.01000,0.366
|
| 52 |
+
7,self_attn.v_proj,0.00139370,0.01000,0.148
|
| 53 |
+
7,self_attn.q_proj,0.00637256,0.01000,0.142
|
| 54 |
+
7,self_attn.o_proj,0.00216803,0.01000,1.421
|
| 55 |
+
7,mlp.up_proj,0.00479016,0.01000,0.280
|
| 56 |
+
7,mlp.gate_proj,0.00473948,0.01000,0.287
|
| 57 |
+
7,mlp.down_proj,0.00823352,0.01000,0.831
|
| 58 |
+
8,self_attn.k_proj,0.00214538,0.01000,1.666
|
| 59 |
+
8,self_attn.v_proj,0.00103131,0.01000,1.952
|
| 60 |
+
8,self_attn.q_proj,0.00540090,0.01000,1.636
|
| 61 |
+
8,self_attn.o_proj,0.00283757,0.01000,0.303
|
| 62 |
+
8,mlp.up_proj,0.00546549,0.01000,0.274
|
| 63 |
+
8,mlp.gate_proj,0.00495393,0.01000,0.275
|
| 64 |
+
8,mlp.down_proj,0.01154038,0.01000,6.464
|
| 65 |
+
9,self_attn.k_proj,0.00147208,0.01000,1.818
|
| 66 |
+
9,self_attn.v_proj,0.00058141,0.01000,1.731
|
| 67 |
+
9,self_attn.q_proj,0.00394661,0.01000,1.675
|
| 68 |
+
9,self_attn.o_proj,0.00251221,0.01000,0.324
|
| 69 |
+
9,mlp.up_proj,0.00595842,0.01000,0.347
|
| 70 |
+
9,mlp.gate_proj,0.00489875,0.01000,0.343
|
| 71 |
+
9,mlp.down_proj,0.01428184,0.01000,0.904
|
| 72 |
+
10,self_attn.k_proj,0.00132155,0.01000,2.685
|
| 73 |
+
10,self_attn.v_proj,0.00068617,0.01000,2.503
|
| 74 |
+
10,self_attn.q_proj,0.00363028,0.01000,1.752
|
| 75 |
+
10,self_attn.o_proj,0.00545926,0.01000,0.408
|
| 76 |
+
10,mlp.up_proj,0.00611763,0.01000,1.632
|
| 77 |
+
10,mlp.gate_proj,0.00474317,0.01000,1.328
|
| 78 |
+
10,mlp.down_proj,0.01347071,0.01000,2.937
|
| 79 |
+
11,self_attn.k_proj,0.00115821,0.01000,3.339
|
| 80 |
+
11,self_attn.v_proj,0.00065106,0.01000,2.422
|
| 81 |
+
11,self_attn.q_proj,0.00344706,0.01000,2.382
|
| 82 |
+
11,self_attn.o_proj,0.00740811,0.01000,2.400
|
| 83 |
+
11,mlp.up_proj,0.00620620,0.01000,2.718
|
| 84 |
+
11,mlp.gate_proj,0.00449832,0.01000,2.710
|
| 85 |
+
11,mlp.down_proj,0.27257532,0.01000,5.754
|
| 86 |
+
12,self_attn.k_proj,0.00163961,0.01000,0.344
|
| 87 |
+
12,self_attn.v_proj,0.00094356,0.01000,0.337
|
| 88 |
+
12,self_attn.q_proj,0.00456318,0.01000,0.338
|
| 89 |
+
12,self_attn.o_proj,0.00419531,0.01000,1.311
|
| 90 |
+
12,mlp.up_proj,0.00565002,0.01000,0.279
|
| 91 |
+
12,mlp.gate_proj,0.00445975,0.01000,1.091
|
| 92 |
+
12,mlp.down_proj,0.01192240,0.01000,4.327
|
| 93 |
+
13,self_attn.k_proj,0.00174242,0.01000,0.339
|
| 94 |
+
13,self_attn.v_proj,0.00083272,0.01000,0.344
|
| 95 |
+
13,self_attn.q_proj,0.00502530,0.01000,0.395
|
| 96 |
+
13,self_attn.o_proj,0.00500150,0.01000,0.343
|
| 97 |
+
13,mlp.up_proj,0.00570113,0.01000,1.926
|
| 98 |
+
13,mlp.gate_proj,0.00524486,0.01000,1.750
|
| 99 |
+
13,mlp.down_proj,0.01178209,0.01000,2.821
|
| 100 |
+
14,self_attn.k_proj,0.00200629,0.01000,0.361
|
| 101 |
+
14,self_attn.v_proj,0.00157519,0.01000,0.359
|
| 102 |
+
14,self_attn.q_proj,0.00566488,0.01000,0.366
|
| 103 |
+
14,self_attn.o_proj,0.00620107,0.01000,2.248
|
| 104 |
+
14,mlp.up_proj,0.00577955,0.01000,4.655
|
| 105 |
+
14,mlp.gate_proj,0.00547774,0.01000,5.042
|
| 106 |
+
14,mlp.down_proj,0.01469438,0.01000,8.832
|
| 107 |
+
15,self_attn.k_proj,0.00194205,0.01000,0.349
|
| 108 |
+
15,self_attn.v_proj,0.00151308,0.01000,0.345
|
| 109 |
+
15,self_attn.q_proj,0.00563300,0.01000,0.342
|
| 110 |
+
15,self_attn.o_proj,0.00601548,0.01000,0.344
|
| 111 |
+
15,mlp.up_proj,0.00601284,0.01000,0.342
|
| 112 |
+
15,mlp.gate_proj,0.00594717,0.01000,0.336
|
| 113 |
+
15,mlp.down_proj,0.01753610,0.01000,5.689
|
| 114 |
+
16,self_attn.k_proj,0.00155090,0.01000,1.763
|
| 115 |
+
16,self_attn.v_proj,0.00110804,0.01000,0.365
|
| 116 |
+
16,self_attn.q_proj,0.00422240,0.01000,0.357
|
| 117 |
+
16,self_attn.o_proj,0.00903260,0.01000,0.345
|
| 118 |
+
16,mlp.up_proj,0.00553630,0.01000,1.181
|
| 119 |
+
16,mlp.gate_proj,0.00532908,0.01000,1.499
|
| 120 |
+
16,mlp.down_proj,0.01532181,0.01000,5.315
|
| 121 |
+
17,self_attn.k_proj,0.00241632,0.01000,0.830
|
| 122 |
+
17,self_attn.v_proj,0.00194845,0.01000,2.641
|
| 123 |
+
17,self_attn.q_proj,0.00834111,0.01000,4.413
|
| 124 |
+
17,self_attn.o_proj,0.01061929,0.01000,2.746
|
| 125 |
+
17,mlp.up_proj,0.00562216,0.01000,2.742
|
| 126 |
+
17,mlp.gate_proj,0.00506327,0.01000,1.101
|
| 127 |
+
17,mlp.down_proj,0.01818097,0.01000,4.789
|
| 128 |
+
18,self_attn.k_proj,0.00273163,0.01000,2.613
|
| 129 |
+
18,self_attn.v_proj,0.00311299,0.01000,1.891
|
| 130 |
+
18,self_attn.q_proj,0.00828936,0.01000,0.344
|
| 131 |
+
18,self_attn.o_proj,0.00938506,0.01000,0.345
|
| 132 |
+
18,mlp.up_proj,0.00625932,0.01000,0.344
|
| 133 |
+
18,mlp.gate_proj,0.00583430,0.01000,0.339
|
| 134 |
+
18,mlp.down_proj,0.03318551,0.01000,2.234
|
| 135 |
+
19,self_attn.k_proj,0.00133622,0.01000,0.326
|
| 136 |
+
19,self_attn.v_proj,0.00225405,0.01000,0.800
|
| 137 |
+
19,self_attn.q_proj,0.00550781,0.01000,1.800
|
| 138 |
+
19,self_attn.o_proj,0.01567704,0.01000,0.449
|
| 139 |
+
19,mlp.up_proj,0.00725614,0.01000,2.903
|
| 140 |
+
19,mlp.gate_proj,0.00687203,0.01000,2.471
|
| 141 |
+
19,mlp.down_proj,0.03395692,0.01000,2.946
|
| 142 |
+
20,self_attn.k_proj,0.00182818,0.01000,0.388
|
| 143 |
+
20,self_attn.v_proj,0.00369986,0.01000,1.045
|
| 144 |
+
20,self_attn.q_proj,0.00668970,0.01000,3.772
|
| 145 |
+
20,self_attn.o_proj,0.01447436,0.01000,3.580
|
| 146 |
+
20,mlp.up_proj,0.00868652,0.01000,2.710
|
| 147 |
+
20,mlp.gate_proj,0.00763109,0.01000,1.037
|
| 148 |
+
20,mlp.down_proj,0.06614500,0.01000,3.153
|
| 149 |
+
21,self_attn.k_proj,0.00169165,0.01000,0.353
|
| 150 |
+
21,self_attn.v_proj,0.00278996,0.01000,1.556
|
| 151 |
+
21,self_attn.q_proj,0.00603606,0.01000,2.608
|
| 152 |
+
21,self_attn.o_proj,0.01160419,0.01000,2.633
|
| 153 |
+
21,mlp.up_proj,0.00941546,0.01000,2.761
|
| 154 |
+
21,mlp.gate_proj,0.00857336,0.01000,1.637
|
| 155 |
+
21,mlp.down_proj,0.05236044,0.01000,3.023
|
| 156 |
+
22,self_attn.k_proj,0.00173458,0.01000,0.340
|
| 157 |
+
22,self_attn.v_proj,0.00304587,0.01000,0.335
|
| 158 |
+
22,self_attn.q_proj,0.00609978,0.01000,1.500
|
| 159 |
+
22,self_attn.o_proj,0.01699413,0.01000,0.329
|
| 160 |
+
22,mlp.up_proj,0.01043702,0.01000,3.157
|
| 161 |
+
22,mlp.gate_proj,0.00901166,0.01000,2.403
|
| 162 |
+
22,mlp.down_proj,0.08635419,0.01000,2.277
|
| 163 |
+
23,self_attn.k_proj,0.00235798,0.01000,2.724
|
| 164 |
+
23,self_attn.v_proj,0.00853371,0.01000,2.700
|
| 165 |
+
23,self_attn.q_proj,0.00731025,0.01000,2.679
|
| 166 |
+
23,self_attn.o_proj,0.04595792,0.01000,0.347
|
| 167 |
+
23,mlp.up_proj,0.01267573,0.01000,1.922
|
| 168 |
+
23,mlp.gate_proj,0.00977481,0.01000,1.572
|
| 169 |
+
23,mlp.down_proj,0.09878369,0.01000,1.992
|
| 170 |
+
24,self_attn.k_proj,0.00193833,0.01000,0.352
|
| 171 |
+
24,self_attn.v_proj,0.00926276,0.01000,0.343
|
| 172 |
+
24,self_attn.q_proj,0.00732911,0.01000,0.354
|
| 173 |
+
24,self_attn.o_proj,0.02490180,0.01000,0.294
|
| 174 |
+
24,mlp.up_proj,0.01275103,0.01000,3.643
|
| 175 |
+
24,mlp.gate_proj,0.00968059,0.01000,4.339
|
| 176 |
+
24,mlp.down_proj,0.13135986,0.01000,6.748
|
| 177 |
+
25,self_attn.k_proj,0.00188807,0.01000,1.592
|
| 178 |
+
25,self_attn.v_proj,0.00410724,0.01000,1.087
|
| 179 |
+
25,self_attn.q_proj,0.00648702,0.01000,0.338
|
| 180 |
+
25,self_attn.o_proj,0.01829978,0.01000,1.828
|
| 181 |
+
25,mlp.up_proj,0.01323432,0.01000,0.353
|
| 182 |
+
25,mlp.gate_proj,0.01043347,0.01000,0.343
|
| 183 |
+
25,mlp.down_proj,0.10982227,0.01000,6.597
|
| 184 |
+
26,self_attn.k_proj,0.00186195,0.01000,3.885
|
| 185 |
+
26,self_attn.v_proj,0.00593649,0.01000,2.686
|
| 186 |
+
26,self_attn.q_proj,0.00663982,0.01000,0.818
|
| 187 |
+
26,self_attn.o_proj,0.02385299,0.01000,0.346
|
| 188 |
+
26,mlp.up_proj,0.01519259,0.01000,0.357
|
| 189 |
+
26,mlp.gate_proj,0.01179895,0.01000,0.383
|
| 190 |
+
26,mlp.down_proj,0.16240232,0.01000,2.805
|
| 191 |
+
27,self_attn.k_proj,0.00188216,0.01000,0.753
|
| 192 |
+
27,self_attn.v_proj,0.00480582,0.01000,2.568
|
| 193 |
+
27,self_attn.q_proj,0.00687713,0.01000,3.243
|
| 194 |
+
27,self_attn.o_proj,0.03130198,0.01000,1.944
|
| 195 |
+
27,mlp.up_proj,0.01527163,0.01000,0.361
|
| 196 |
+
27,mlp.gate_proj,0.01144433,0.01000,0.350
|
| 197 |
+
27,mlp.down_proj,0.20937583,0.01000,6.981
|
| 198 |
+
28,self_attn.k_proj,0.00163398,0.01000,2.274
|
| 199 |
+
28,self_attn.v_proj,0.00619308,0.01000,0.347
|
| 200 |
+
28,self_attn.q_proj,0.00561940,0.01000,1.200
|
| 201 |
+
28,self_attn.o_proj,0.02704479,0.01000,0.391
|
| 202 |
+
28,mlp.up_proj,0.01647252,0.01000,0.362
|
| 203 |
+
28,mlp.gate_proj,0.01167521,0.01000,0.348
|
| 204 |
+
28,mlp.down_proj,3.19434714,0.01000,7.166
|
| 205 |
+
29,self_attn.k_proj,0.00153822,0.01000,1.574
|
| 206 |
+
29,self_attn.v_proj,0.00717453,0.01000,0.978
|
| 207 |
+
29,self_attn.q_proj,0.00649254,0.01000,1.795
|
| 208 |
+
29,self_attn.o_proj,0.06275121,0.01000,0.949
|
| 209 |
+
29,mlp.up_proj,0.02440672,0.01000,2.122
|
| 210 |
+
29,mlp.gate_proj,0.01807862,0.01000,0.632
|
| 211 |
+
29,mlp.down_proj,0.86159390,0.01000,0.909
|
quantize_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 8,
|
| 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:2.1.1-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 |
+
}
|
| 21 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|im_end|>",
|
| 21 |
+
"unk_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
}
|
| 28 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
+
"clean_up_tokenization_spaces": false,
|
| 148 |
+
"eos_token": "<|im_end|>",
|
| 149 |
+
"extra_special_tokens": {},
|
| 150 |
+
"model_max_length": 8192,
|
| 151 |
+
"pad_token": "<|im_end|>",
|
| 152 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
| 153 |
+
"unk_token": "<|endoftext|>",
|
| 154 |
+
"vocab_size": 49152,
|
| 155 |
+
"_commit_hash": null
|
| 156 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|