Upload folder using huggingface_hub
Browse files- added_tokens.json +13 -0
- config.json +269 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +131 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "phi3",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Phi3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"embd_pdrop": 0.0,
|
| 14 |
+
"eos_token_id": 32000,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 3072,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"original_max_position_embeddings": 4096,
|
| 21 |
+
"pad_token_id": 32000,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"long_factor": [
|
| 26 |
+
1.0700000524520874,
|
| 27 |
+
1.1200000047683716,
|
| 28 |
+
1.149999976158142,
|
| 29 |
+
1.4199999570846558,
|
| 30 |
+
1.5699999332427979,
|
| 31 |
+
1.7999999523162842,
|
| 32 |
+
2.129999876022339,
|
| 33 |
+
2.129999876022339,
|
| 34 |
+
3.009999990463257,
|
| 35 |
+
5.910000324249268,
|
| 36 |
+
6.950000286102295,
|
| 37 |
+
9.070000648498535,
|
| 38 |
+
9.930000305175781,
|
| 39 |
+
10.710000038146973,
|
| 40 |
+
11.130000114440918,
|
| 41 |
+
14.609999656677246,
|
| 42 |
+
15.409998893737793,
|
| 43 |
+
19.809999465942383,
|
| 44 |
+
37.279998779296875,
|
| 45 |
+
38.279998779296875,
|
| 46 |
+
38.599998474121094,
|
| 47 |
+
40.12000274658203,
|
| 48 |
+
46.20000457763672,
|
| 49 |
+
50.940006256103516,
|
| 50 |
+
53.66000747680664,
|
| 51 |
+
54.9373893737793,
|
| 52 |
+
56.89738845825195,
|
| 53 |
+
57.28738784790039,
|
| 54 |
+
59.98738479614258,
|
| 55 |
+
60.86738586425781,
|
| 56 |
+
60.887386322021484,
|
| 57 |
+
61.71739196777344,
|
| 58 |
+
62.91739273071289,
|
| 59 |
+
62.957393646240234,
|
| 60 |
+
63.41739273071289,
|
| 61 |
+
63.8173942565918,
|
| 62 |
+
63.83739471435547,
|
| 63 |
+
63.897396087646484,
|
| 64 |
+
63.93739700317383,
|
| 65 |
+
64.06739807128906,
|
| 66 |
+
64.11434936523438,
|
| 67 |
+
64.12435150146484,
|
| 68 |
+
64.15435028076172,
|
| 69 |
+
64.19435119628906,
|
| 70 |
+
64.24435424804688,
|
| 71 |
+
64.57435607910156,
|
| 72 |
+
64.69000244140625,
|
| 73 |
+
64.76000213623047
|
| 74 |
+
],
|
| 75 |
+
"short_factor": [
|
| 76 |
+
1.1,
|
| 77 |
+
1.1,
|
| 78 |
+
1.1,
|
| 79 |
+
1.3000000000000003,
|
| 80 |
+
1.3500000000000003,
|
| 81 |
+
1.3500000000000003,
|
| 82 |
+
1.4000000000000004,
|
| 83 |
+
1.5500000000000005,
|
| 84 |
+
2.000000000000001,
|
| 85 |
+
2.000000000000001,
|
| 86 |
+
2.000000000000001,
|
| 87 |
+
2.000000000000001,
|
| 88 |
+
2.000000000000001,
|
| 89 |
+
2.000000000000001,
|
| 90 |
+
2.000000000000001,
|
| 91 |
+
2.000000000000001,
|
| 92 |
+
2.000000000000001,
|
| 93 |
+
2.000000000000001,
|
| 94 |
+
2.000000000000001,
|
| 95 |
+
2.000000000000001,
|
| 96 |
+
2.000000000000001,
|
| 97 |
+
2.000000000000001,
|
| 98 |
+
2.000000000000001,
|
| 99 |
+
2.000000000000001,
|
| 100 |
+
2.000000000000001,
|
| 101 |
+
2.0500000000000007,
|
| 102 |
+
2.0500000000000007,
|
| 103 |
+
2.0500000000000007,
|
| 104 |
+
2.0500000000000007,
|
| 105 |
+
2.0500000000000007,
|
| 106 |
+
2.0500000000000007,
|
| 107 |
+
2.1000000000000005,
|
| 108 |
+
2.1000000000000005,
|
| 109 |
+
2.1500000000000004,
|
| 110 |
+
2.25,
|
| 111 |
+
2.25,
|
| 112 |
+
2.25,
|
| 113 |
+
2.25,
|
| 114 |
+
2.25,
|
| 115 |
+
2.3999999999999995,
|
| 116 |
+
2.4499999999999993,
|
| 117 |
+
2.499999999999999,
|
| 118 |
+
2.6999999999999984,
|
| 119 |
+
2.6999999999999984,
|
| 120 |
+
2.7499999999999982,
|
| 121 |
+
2.799999999999998,
|
| 122 |
+
2.8999999999999977,
|
| 123 |
+
3.049999999999997
|
| 124 |
+
],
|
| 125 |
+
"type": "longrope"
|
| 126 |
+
},
|
| 127 |
+
"rope_theta": 10000.0,
|
| 128 |
+
"sliding_window": 262144,
|
| 129 |
+
"tie_word_embeddings": false,
|
| 130 |
+
"torch_dtype": "float32",
|
| 131 |
+
"transformers_version": "4.42.4",
|
| 132 |
+
"use_cache": true,
|
| 133 |
+
"vocab_size": 32064,
|
| 134 |
+
"peft_type": "LORA",
|
| 135 |
+
"lora_alpha": 32,
|
| 136 |
+
"lora_dropout": 0.05,
|
| 137 |
+
"r": 16,
|
| 138 |
+
"target_modules": [
|
| 139 |
+
"model.layers.15.self_attn.o_proj",
|
| 140 |
+
"model.layers.18.mlp.gate_up_proj",
|
| 141 |
+
"model.layers.3.self_attn.o_proj",
|
| 142 |
+
"model.layers.15.mlp.down_proj",
|
| 143 |
+
"model.layers.20.self_attn.o_proj",
|
| 144 |
+
"model.layers.30.self_attn.o_proj",
|
| 145 |
+
"model.layers.6.mlp.gate_up_proj",
|
| 146 |
+
"model.layers.17.self_attn.qkv_proj",
|
| 147 |
+
"model.layers.4.self_attn.qkv_proj",
|
| 148 |
+
"model.layers.28.self_attn.o_proj",
|
| 149 |
+
"model.layers.3.mlp.down_proj",
|
| 150 |
+
"model.layers.19.mlp.down_proj",
|
| 151 |
+
"model.layers.8.self_attn.o_proj",
|
| 152 |
+
"model.layers.8.mlp.down_proj",
|
| 153 |
+
"model.layers.14.self_attn.qkv_proj",
|
| 154 |
+
"model.layers.23.mlp.gate_up_proj",
|
| 155 |
+
"model.layers.9.self_attn.qkv_proj",
|
| 156 |
+
"model.layers.15.self_attn.qkv_proj",
|
| 157 |
+
"model.layers.2.self_attn.o_proj",
|
| 158 |
+
"model.layers.26.self_attn.qkv_proj",
|
| 159 |
+
"model.layers.7.self_attn.qkv_proj",
|
| 160 |
+
"model.layers.25.self_attn.qkv_proj",
|
| 161 |
+
"model.layers.22.mlp.gate_up_proj",
|
| 162 |
+
"model.layers.8.mlp.gate_up_proj",
|
| 163 |
+
"model.layers.29.mlp.down_proj",
|
| 164 |
+
"model.layers.30.mlp.down_proj",
|
| 165 |
+
"model.layers.20.self_attn.qkv_proj",
|
| 166 |
+
"model.layers.27.self_attn.qkv_proj",
|
| 167 |
+
"model.layers.31.self_attn.o_proj",
|
| 168 |
+
"model.layers.13.mlp.down_proj",
|
| 169 |
+
"model.layers.16.mlp.down_proj",
|
| 170 |
+
"model.layers.9.mlp.down_proj",
|
| 171 |
+
"model.layers.7.mlp.gate_up_proj",
|
| 172 |
+
"model.layers.29.self_attn.qkv_proj",
|
| 173 |
+
"model.layers.29.mlp.gate_up_proj",
|
| 174 |
+
"model.layers.7.mlp.down_proj",
|
| 175 |
+
"model.layers.1.mlp.down_proj",
|
| 176 |
+
"model.layers.19.self_attn.o_proj",
|
| 177 |
+
"model.layers.27.mlp.down_proj",
|
| 178 |
+
"model.layers.26.mlp.gate_up_proj",
|
| 179 |
+
"model.layers.3.self_attn.qkv_proj",
|
| 180 |
+
"model.layers.1.mlp.gate_up_proj",
|
| 181 |
+
"model.layers.17.mlp.gate_up_proj",
|
| 182 |
+
"model.layers.14.mlp.down_proj",
|
| 183 |
+
"model.layers.2.mlp.gate_up_proj",
|
| 184 |
+
"model.layers.11.self_attn.qkv_proj",
|
| 185 |
+
"model.layers.13.mlp.gate_up_proj",
|
| 186 |
+
"model.layers.6.mlp.down_proj",
|
| 187 |
+
"model.layers.19.mlp.gate_up_proj",
|
| 188 |
+
"model.layers.22.self_attn.qkv_proj",
|
| 189 |
+
"model.layers.24.mlp.down_proj",
|
| 190 |
+
"model.layers.18.self_attn.o_proj",
|
| 191 |
+
"model.layers.10.mlp.gate_up_proj",
|
| 192 |
+
"model.layers.25.mlp.gate_up_proj",
|
| 193 |
+
"model.layers.27.mlp.gate_up_proj",
|
| 194 |
+
"model.layers.5.mlp.gate_up_proj",
|
| 195 |
+
"model.layers.4.mlp.down_proj",
|
| 196 |
+
"model.layers.3.mlp.gate_up_proj",
|
| 197 |
+
"model.layers.15.mlp.gate_up_proj",
|
| 198 |
+
"model.layers.25.self_attn.o_proj",
|
| 199 |
+
"model.layers.0.mlp.down_proj",
|
| 200 |
+
"model.layers.21.self_attn.qkv_proj",
|
| 201 |
+
"model.layers.12.self_attn.o_proj",
|
| 202 |
+
"model.layers.28.self_attn.qkv_proj",
|
| 203 |
+
"model.layers.20.mlp.gate_up_proj",
|
| 204 |
+
"model.layers.14.mlp.gate_up_proj",
|
| 205 |
+
"model.layers.20.mlp.down_proj",
|
| 206 |
+
"model.layers.18.self_attn.qkv_proj",
|
| 207 |
+
"model.layers.12.self_attn.qkv_proj",
|
| 208 |
+
"model.layers.25.mlp.down_proj",
|
| 209 |
+
"model.layers.5.self_attn.qkv_proj",
|
| 210 |
+
"model.layers.24.mlp.gate_up_proj",
|
| 211 |
+
"model.layers.23.self_attn.o_proj",
|
| 212 |
+
"model.layers.17.self_attn.o_proj",
|
| 213 |
+
"model.layers.6.self_attn.qkv_proj",
|
| 214 |
+
"model.layers.22.self_attn.o_proj",
|
| 215 |
+
"model.layers.6.self_attn.o_proj",
|
| 216 |
+
"model.layers.31.self_attn.qkv_proj",
|
| 217 |
+
"model.layers.21.self_attn.o_proj",
|
| 218 |
+
"model.layers.7.self_attn.o_proj",
|
| 219 |
+
"model.layers.24.self_attn.qkv_proj",
|
| 220 |
+
"model.layers.16.self_attn.o_proj",
|
| 221 |
+
"model.layers.16.self_attn.qkv_proj",
|
| 222 |
+
"model.layers.12.mlp.down_proj",
|
| 223 |
+
"model.layers.28.mlp.gate_up_proj",
|
| 224 |
+
"model.layers.0.mlp.gate_up_proj",
|
| 225 |
+
"model.layers.9.self_attn.o_proj",
|
| 226 |
+
"model.layers.9.mlp.gate_up_proj",
|
| 227 |
+
"model.layers.5.self_attn.o_proj",
|
| 228 |
+
"model.layers.22.mlp.down_proj",
|
| 229 |
+
"model.layers.24.self_attn.o_proj",
|
| 230 |
+
"model.layers.10.self_attn.qkv_proj",
|
| 231 |
+
"model.layers.1.self_attn.qkv_proj",
|
| 232 |
+
"model.layers.2.mlp.down_proj",
|
| 233 |
+
"model.layers.0.self_attn.qkv_proj",
|
| 234 |
+
"model.layers.8.self_attn.qkv_proj",
|
| 235 |
+
"model.layers.27.self_attn.o_proj",
|
| 236 |
+
"model.layers.5.mlp.down_proj",
|
| 237 |
+
"model.layers.0.self_attn.o_proj",
|
| 238 |
+
"model.layers.26.self_attn.o_proj",
|
| 239 |
+
"model.layers.29.self_attn.o_proj",
|
| 240 |
+
"model.layers.17.mlp.down_proj",
|
| 241 |
+
"model.layers.12.mlp.gate_up_proj",
|
| 242 |
+
"model.layers.10.mlp.down_proj",
|
| 243 |
+
"model.layers.14.self_attn.o_proj",
|
| 244 |
+
"model.layers.13.self_attn.o_proj",
|
| 245 |
+
"model.layers.11.self_attn.o_proj",
|
| 246 |
+
"model.layers.23.mlp.down_proj",
|
| 247 |
+
"model.layers.19.self_attn.qkv_proj",
|
| 248 |
+
"model.layers.31.mlp.down_proj",
|
| 249 |
+
"model.layers.23.self_attn.qkv_proj",
|
| 250 |
+
"model.layers.31.mlp.gate_up_proj",
|
| 251 |
+
"model.layers.30.mlp.gate_up_proj",
|
| 252 |
+
"model.layers.4.mlp.gate_up_proj",
|
| 253 |
+
"model.layers.4.self_attn.o_proj",
|
| 254 |
+
"model.layers.2.self_attn.qkv_proj",
|
| 255 |
+
"model.layers.11.mlp.gate_up_proj",
|
| 256 |
+
"model.layers.13.self_attn.qkv_proj",
|
| 257 |
+
"model.layers.21.mlp.gate_up_proj",
|
| 258 |
+
"model.layers.18.mlp.down_proj",
|
| 259 |
+
"model.layers.26.mlp.down_proj",
|
| 260 |
+
"model.layers.10.self_attn.o_proj",
|
| 261 |
+
"model.layers.11.mlp.down_proj",
|
| 262 |
+
"model.layers.21.mlp.down_proj",
|
| 263 |
+
"model.layers.30.self_attn.qkv_proj",
|
| 264 |
+
"model.layers.1.self_attn.o_proj",
|
| 265 |
+
"model.layers.28.mlp.down_proj",
|
| 266 |
+
"model.layers.16.mlp.gate_up_proj"
|
| 267 |
+
],
|
| 268 |
+
"num_hidden_layers": 32
|
| 269 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ebe90480a5467fea616022a89f1c7496f8d1f26b4da08aa4dc252b875cc20b7
|
| 3 |
+
size 15284405759
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 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 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 131072,
|
| 125 |
+
"pad_token": "<|endoftext|>",
|
| 126 |
+
"padding_side": "left",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 129 |
+
"unk_token": "<unk>",
|
| 130 |
+
"use_default_system_prompt": false
|
| 131 |
+
}
|