Upload folder using huggingface_hub
Browse files- added_tokens.json +40 -0
- config.json +51 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +193 -0
- quantize_config.json +21 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +325 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "D:\\Phi2\\phi-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 10240,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "phi",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"partial_rotary_factor": 0.4,
|
| 21 |
+
"qk_layernorm": false,
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"bits": 8,
|
| 24 |
+
"checkpoint_format": "gptq",
|
| 25 |
+
"desc_act": true,
|
| 26 |
+
"group_size": 128,
|
| 27 |
+
"lm_head": false,
|
| 28 |
+
"meta": {
|
| 29 |
+
"damp_auto_increment": 0.0025,
|
| 30 |
+
"damp_percent": 0.01,
|
| 31 |
+
"mse": 0.0,
|
| 32 |
+
"quantizer": [
|
| 33 |
+
"gptqmodel:2.2.0"
|
| 34 |
+
],
|
| 35 |
+
"static_groups": false,
|
| 36 |
+
"true_sequential": true,
|
| 37 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 38 |
+
},
|
| 39 |
+
"pack_dtype": "int32",
|
| 40 |
+
"quant_method": "gptq",
|
| 41 |
+
"sym": true
|
| 42 |
+
},
|
| 43 |
+
"resid_pdrop": 0.1,
|
| 44 |
+
"rope_scaling": null,
|
| 45 |
+
"rope_theta": 10000.0,
|
| 46 |
+
"tie_word_embeddings": false,
|
| 47 |
+
"torch_dtype": "float16",
|
| 48 |
+
"transformers_version": "4.49.0",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 51200
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.49.0"
|
| 6 |
+
}
|
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:e488b8affca490ea4a41ba5cc3a8e3e6f899ce8e72da16fcb0e79c7d6cddcf2c
|
| 3 |
+
size 3104829568
|
quant_log.csv
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.q_proj,0.00143004,0.01000,1.666
|
| 3 |
+
0,self_attn.k_proj,0.00152641,0.01000,1.244
|
| 4 |
+
0,self_attn.v_proj,0.00055014,0.01000,1.224
|
| 5 |
+
0,self_attn.dense,0.00040645,0.01000,1.199
|
| 6 |
+
0,mlp.fc1,0.00156395,0.01000,1.471
|
| 7 |
+
0,mlp.fc2,45.18684896,0.01250,8.215
|
| 8 |
+
1,self_attn.q_proj,0.00098901,0.01000,1.230
|
| 9 |
+
1,self_attn.k_proj,0.00098037,0.01000,1.193
|
| 10 |
+
1,self_attn.v_proj,0.00025730,0.01000,1.200
|
| 11 |
+
1,self_attn.dense,0.00010639,0.01000,1.247
|
| 12 |
+
1,mlp.fc1,0.00321254,0.01000,1.491
|
| 13 |
+
1,mlp.fc2,47.71025594,0.01250,8.363
|
| 14 |
+
2,self_attn.q_proj,0.00124894,0.01000,1.345
|
| 15 |
+
2,self_attn.k_proj,0.00125460,0.01000,1.299
|
| 16 |
+
2,self_attn.v_proj,0.00052309,0.01000,1.253
|
| 17 |
+
2,self_attn.dense,0.00011987,0.01000,1.390
|
| 18 |
+
2,mlp.fc1,0.00455974,0.01000,1.709
|
| 19 |
+
2,mlp.fc2,51.62885539,0.01250,8.104
|
| 20 |
+
3,self_attn.q_proj,0.00130572,0.01000,1.189
|
| 21 |
+
3,self_attn.k_proj,0.00125844,0.01000,1.239
|
| 22 |
+
3,self_attn.v_proj,0.00100104,0.01000,1.399
|
| 23 |
+
3,self_attn.dense,0.00010456,0.01000,1.400
|
| 24 |
+
3,mlp.fc1,0.00656331,0.01000,1.650
|
| 25 |
+
3,mlp.fc2,52.00990804,0.01250,8.130
|
| 26 |
+
4,self_attn.q_proj,0.00165055,0.01000,1.275
|
| 27 |
+
4,self_attn.k_proj,0.00151279,0.01000,1.267
|
| 28 |
+
4,self_attn.v_proj,0.00109894,0.01000,1.210
|
| 29 |
+
4,self_attn.dense,0.00008104,0.01000,1.164
|
| 30 |
+
4,mlp.fc1,0.00635077,0.01000,1.470
|
| 31 |
+
4,mlp.fc2,45.79121908,0.01250,7.909
|
| 32 |
+
5,self_attn.q_proj,0.00146975,0.01000,1.218
|
| 33 |
+
5,self_attn.k_proj,0.00134510,0.01000,1.212
|
| 34 |
+
5,self_attn.v_proj,0.00096357,0.01000,1.230
|
| 35 |
+
5,self_attn.dense,0.00009522,0.01000,1.167
|
| 36 |
+
5,mlp.fc1,0.00543682,0.01000,1.510
|
| 37 |
+
5,mlp.fc2,39.91021474,0.01250,8.151
|
| 38 |
+
6,self_attn.q_proj,0.00179219,0.01000,1.304
|
| 39 |
+
6,self_attn.k_proj,0.00164673,0.01000,1.153
|
| 40 |
+
6,self_attn.v_proj,0.00118458,0.01000,1.130
|
| 41 |
+
6,self_attn.dense,0.00008672,0.01000,1.179
|
| 42 |
+
6,mlp.fc1,0.00587255,0.01000,1.484
|
| 43 |
+
6,mlp.fc2,44.64824422,0.01250,8.148
|
| 44 |
+
7,self_attn.q_proj,0.00186776,0.01000,1.171
|
| 45 |
+
7,self_attn.k_proj,0.00177774,0.01000,1.137
|
| 46 |
+
7,self_attn.v_proj,0.00120310,0.01000,1.267
|
| 47 |
+
7,self_attn.dense,0.00006188,0.01000,1.291
|
| 48 |
+
7,mlp.fc1,0.00593133,0.01000,1.634
|
| 49 |
+
7,mlp.fc2,39.13363139,0.01250,8.085
|
| 50 |
+
8,self_attn.q_proj,0.00189651,0.01000,1.240
|
| 51 |
+
8,self_attn.k_proj,0.00176293,0.01000,1.228
|
| 52 |
+
8,self_attn.v_proj,0.00140262,0.01000,1.245
|
| 53 |
+
8,self_attn.dense,0.00006599,0.01000,1.192
|
| 54 |
+
8,mlp.fc1,0.00588503,0.01000,1.698
|
| 55 |
+
8,mlp.fc2,40.45288086,0.01250,8.500
|
| 56 |
+
9,self_attn.q_proj,0.00191524,0.01000,1.303
|
| 57 |
+
9,self_attn.k_proj,0.00177061,0.01000,1.146
|
| 58 |
+
9,self_attn.v_proj,0.00140069,0.01000,1.155
|
| 59 |
+
9,self_attn.dense,0.00008725,0.01000,1.173
|
| 60 |
+
9,mlp.fc1,0.00577327,0.01000,1.504
|
| 61 |
+
9,mlp.fc2,41.11215210,0.01250,8.315
|
| 62 |
+
10,self_attn.q_proj,0.00192486,0.01000,1.232
|
| 63 |
+
10,self_attn.k_proj,0.00184659,0.01000,1.287
|
| 64 |
+
10,self_attn.v_proj,0.00122425,0.01000,1.217
|
| 65 |
+
10,self_attn.dense,0.00008808,0.01000,1.212
|
| 66 |
+
10,mlp.fc1,0.00560408,0.01000,1.617
|
| 67 |
+
10,mlp.fc2,38.80376689,0.01250,8.274
|
| 68 |
+
11,self_attn.q_proj,0.00201942,0.01000,1.267
|
| 69 |
+
11,self_attn.k_proj,0.00193283,0.01000,1.240
|
| 70 |
+
11,self_attn.v_proj,0.00134693,0.01000,1.196
|
| 71 |
+
11,self_attn.dense,0.00010903,0.01000,1.279
|
| 72 |
+
11,mlp.fc1,0.00545754,0.01000,1.536
|
| 73 |
+
11,mlp.fc2,38.56307475,0.01250,7.950
|
| 74 |
+
12,self_attn.q_proj,0.00209887,0.01000,1.200
|
| 75 |
+
12,self_attn.k_proj,0.00200503,0.01000,1.235
|
| 76 |
+
12,self_attn.v_proj,0.00137541,0.01000,1.226
|
| 77 |
+
12,self_attn.dense,0.00008138,0.01000,1.221
|
| 78 |
+
12,mlp.fc1,0.00540713,0.01000,1.525
|
| 79 |
+
12,mlp.fc2,40.88318888,0.01250,8.217
|
| 80 |
+
13,self_attn.q_proj,0.00200631,0.01000,1.251
|
| 81 |
+
13,self_attn.k_proj,0.00194197,0.01000,1.219
|
| 82 |
+
13,self_attn.v_proj,0.00134296,0.01000,1.149
|
| 83 |
+
13,self_attn.dense,0.00007691,0.01000,1.237
|
| 84 |
+
13,mlp.fc1,0.00549893,0.01000,1.499
|
| 85 |
+
13,mlp.fc2,41.56899770,0.01250,8.045
|
| 86 |
+
14,self_attn.q_proj,0.00210726,0.01000,1.282
|
| 87 |
+
14,self_attn.k_proj,0.00314308,0.01000,1.203
|
| 88 |
+
14,self_attn.v_proj,0.00133068,0.01000,1.242
|
| 89 |
+
14,self_attn.dense,0.00009206,0.01000,1.209
|
| 90 |
+
14,mlp.fc1,0.00539970,0.01000,1.479
|
| 91 |
+
14,mlp.fc2,41.86838531,0.01250,8.351
|
| 92 |
+
15,self_attn.q_proj,0.00199632,0.01000,1.302
|
| 93 |
+
15,self_attn.k_proj,0.00192289,0.01000,1.252
|
| 94 |
+
15,self_attn.v_proj,0.00126881,0.01000,1.190
|
| 95 |
+
15,self_attn.dense,0.00010529,0.01000,1.233
|
| 96 |
+
15,mlp.fc1,0.00512260,0.01000,1.654
|
| 97 |
+
15,mlp.fc2,40.16023763,0.01250,8.171
|
| 98 |
+
16,self_attn.q_proj,0.00206465,0.01000,1.269
|
| 99 |
+
16,self_attn.k_proj,0.00198583,0.01000,1.272
|
| 100 |
+
16,self_attn.v_proj,0.00134773,0.01000,1.218
|
| 101 |
+
16,self_attn.dense,0.00011100,0.01000,1.248
|
| 102 |
+
16,mlp.fc1,0.00523687,0.01000,1.613
|
| 103 |
+
16,mlp.fc2,44.88688151,0.01250,8.167
|
| 104 |
+
17,self_attn.q_proj,0.00197861,0.01000,1.327
|
| 105 |
+
17,self_attn.k_proj,0.00189119,0.01000,1.293
|
| 106 |
+
17,self_attn.v_proj,0.00124682,0.01000,1.285
|
| 107 |
+
17,self_attn.dense,0.00008207,0.01000,1.278
|
| 108 |
+
17,mlp.fc1,0.00489658,0.01000,1.480
|
| 109 |
+
17,mlp.fc2,41.40846761,0.01250,8.204
|
| 110 |
+
18,self_attn.q_proj,0.00228992,0.01000,1.315
|
| 111 |
+
18,self_attn.k_proj,0.00217069,0.01000,1.268
|
| 112 |
+
18,self_attn.v_proj,0.00131716,0.01000,1.255
|
| 113 |
+
18,self_attn.dense,0.00008202,0.01000,1.252
|
| 114 |
+
18,mlp.fc1,0.00499909,0.01000,1.578
|
| 115 |
+
18,mlp.fc2,41.80710856,0.01250,8.319
|
| 116 |
+
19,self_attn.q_proj,0.00216272,0.01000,1.389
|
| 117 |
+
19,self_attn.k_proj,0.00209569,0.01000,1.459
|
| 118 |
+
19,self_attn.v_proj,0.00134877,0.01000,1.276
|
| 119 |
+
19,self_attn.dense,0.00010894,0.01000,1.240
|
| 120 |
+
19,mlp.fc1,0.00535385,0.01000,1.577
|
| 121 |
+
19,mlp.fc2,50.55662028,0.01250,8.463
|
| 122 |
+
20,self_attn.q_proj,0.00229107,0.01000,1.262
|
| 123 |
+
20,self_attn.k_proj,0.03851147,0.01000,1.216
|
| 124 |
+
20,self_attn.v_proj,0.00130100,0.01000,1.126
|
| 125 |
+
20,self_attn.dense,0.00012769,0.01000,1.188
|
| 126 |
+
20,mlp.fc1,0.00545297,0.01000,1.534
|
| 127 |
+
20,mlp.fc2,49.51214600,0.01250,8.264
|
| 128 |
+
21,self_attn.q_proj,0.00218866,0.01000,1.271
|
| 129 |
+
21,self_attn.k_proj,0.00204123,0.01000,1.301
|
| 130 |
+
21,self_attn.v_proj,0.00156515,0.01000,1.246
|
| 131 |
+
21,self_attn.dense,0.00012658,0.01000,1.226
|
| 132 |
+
21,mlp.fc1,0.00584921,0.01000,1.567
|
| 133 |
+
21,mlp.fc2,52.78467306,0.01250,8.395
|
| 134 |
+
22,self_attn.q_proj,0.00225957,0.01000,1.327
|
| 135 |
+
22,self_attn.k_proj,0.00357083,0.01000,1.294
|
| 136 |
+
22,self_attn.v_proj,0.00164564,0.01000,1.182
|
| 137 |
+
22,self_attn.dense,0.00010589,0.01000,1.298
|
| 138 |
+
22,mlp.fc1,0.00612155,0.01000,1.662
|
| 139 |
+
22,mlp.fc2,52.80789185,0.01250,8.462
|
| 140 |
+
23,self_attn.q_proj,0.00243160,0.01000,1.332
|
| 141 |
+
23,self_attn.k_proj,0.00276039,0.01000,1.332
|
| 142 |
+
23,self_attn.v_proj,0.00159178,0.01000,1.117
|
| 143 |
+
23,self_attn.dense,0.00016935,0.01000,1.254
|
| 144 |
+
23,mlp.fc1,0.00641046,0.01000,1.594
|
| 145 |
+
23,mlp.fc2,52.62599691,0.01250,8.410
|
| 146 |
+
24,self_attn.q_proj,0.00232852,0.01000,1.257
|
| 147 |
+
24,self_attn.k_proj,0.00215273,0.01000,1.328
|
| 148 |
+
24,self_attn.v_proj,0.00190273,0.01000,1.293
|
| 149 |
+
24,self_attn.dense,0.00019747,0.01000,1.250
|
| 150 |
+
24,mlp.fc1,0.00686966,0.01000,1.517
|
| 151 |
+
24,mlp.fc2,55.26352437,0.01250,8.156
|
| 152 |
+
25,self_attn.q_proj,0.00253579,0.01000,1.216
|
| 153 |
+
25,self_attn.k_proj,0.01635120,0.01000,1.195
|
| 154 |
+
25,self_attn.v_proj,0.00198928,0.01000,1.303
|
| 155 |
+
25,self_attn.dense,0.00024381,0.01000,1.295
|
| 156 |
+
25,mlp.fc1,0.00749265,0.01000,1.487
|
| 157 |
+
25,mlp.fc2,52.59010824,0.01250,8.389
|
| 158 |
+
26,self_attn.q_proj,0.00319071,0.01000,1.357
|
| 159 |
+
26,self_attn.k_proj,0.00231659,0.01000,1.326
|
| 160 |
+
26,self_attn.v_proj,0.00232149,0.01000,1.287
|
| 161 |
+
26,self_attn.dense,0.00024788,0.01000,1.330
|
| 162 |
+
26,mlp.fc1,0.00773018,0.01000,1.644
|
| 163 |
+
26,mlp.fc2,50.22942098,0.01250,8.381
|
| 164 |
+
27,self_attn.q_proj,0.00275840,0.01000,1.284
|
| 165 |
+
27,self_attn.k_proj,0.00304915,0.01000,1.255
|
| 166 |
+
27,self_attn.v_proj,0.00238565,0.01000,1.236
|
| 167 |
+
27,self_attn.dense,0.00028637,0.01000,1.232
|
| 168 |
+
27,mlp.fc1,0.00808649,0.01000,1.501
|
| 169 |
+
27,mlp.fc2,48.66911825,0.01250,8.210
|
| 170 |
+
28,self_attn.q_proj,0.00248579,0.01000,1.194
|
| 171 |
+
28,self_attn.k_proj,0.00226670,0.01000,1.181
|
| 172 |
+
28,self_attn.v_proj,0.00246282,0.01000,1.183
|
| 173 |
+
28,self_attn.dense,0.00041967,0.01000,1.281
|
| 174 |
+
28,mlp.fc1,0.00824952,0.01000,1.527
|
| 175 |
+
28,mlp.fc2,43.05557760,0.01250,8.224
|
| 176 |
+
29,self_attn.q_proj,0.11153113,0.01000,1.266
|
| 177 |
+
29,self_attn.k_proj,0.64342054,0.01000,1.226
|
| 178 |
+
29,self_attn.v_proj,0.00479308,0.01000,1.228
|
| 179 |
+
29,self_attn.dense,0.00025549,0.01000,1.224
|
| 180 |
+
29,mlp.fc1,0.03276892,0.01000,1.495
|
| 181 |
+
29,mlp.fc2,36.04873657,0.01250,8.129
|
| 182 |
+
30,self_attn.q_proj,0.06741060,0.01000,1.441
|
| 183 |
+
30,self_attn.k_proj,0.70108302,0.01000,1.260
|
| 184 |
+
30,self_attn.v_proj,0.00279436,0.01000,1.327
|
| 185 |
+
30,self_attn.dense,0.00033670,0.01000,1.297
|
| 186 |
+
30,mlp.fc1,0.02931402,0.01000,1.595
|
| 187 |
+
30,mlp.fc2,32.39466349,0.01250,8.556
|
| 188 |
+
31,self_attn.q_proj,0.03431750,0.01000,1.214
|
| 189 |
+
31,self_attn.k_proj,5.91425705,0.01000,1.192
|
| 190 |
+
31,self_attn.v_proj,0.00139703,0.01000,1.202
|
| 191 |
+
31,self_attn.dense,0.00031197,0.01000,1.166
|
| 192 |
+
31,mlp.fc1,0.01573335,0.01000,1.476
|
| 193 |
+
31,mlp.fc2,58.13183085,0.01250,8.144
|
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:2.2.0"
|
| 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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"extra_special_tokens": {},
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"return_token_type_ids": false,
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|