add model file
Browse filesSigned-off-by: wenhuach <wenhuach87@gmail.com>
- added_tokens.json +5 -0
- config.json +397 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantization_config.json +360 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/data5/models/Qwen2-57B-A14B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2MoeForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"eos_token_id": 151643,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 3584,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 18944,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"mlp_only_layers": [],
|
| 17 |
+
"model_type": "qwen2_moe",
|
| 18 |
+
"moe_intermediate_size": 2560,
|
| 19 |
+
"norm_topk_prob": false,
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_experts": 64,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"num_hidden_layers": 28,
|
| 24 |
+
"num_key_value_heads": 4,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"amp": true,
|
| 28 |
+
"autoround_version": "0.3.0.dev",
|
| 29 |
+
"backend": "auto_round:exllamav2",
|
| 30 |
+
"bits": 4,
|
| 31 |
+
"data_type": "int",
|
| 32 |
+
"dataset": "NeelNanda/pile-10k",
|
| 33 |
+
"enable_minmax_tuning": true,
|
| 34 |
+
"enable_quanted_input": true,
|
| 35 |
+
"extra_config": {
|
| 36 |
+
"model.layers.0.mlp.gate": {
|
| 37 |
+
"bits": 32,
|
| 38 |
+
"data_type": "bfloat",
|
| 39 |
+
"group_size": null,
|
| 40 |
+
"sym": null
|
| 41 |
+
},
|
| 42 |
+
"model.layers.0.mlp.shared_expert_gate": {
|
| 43 |
+
"bits": 32,
|
| 44 |
+
"data_type": "bfloat",
|
| 45 |
+
"group_size": null,
|
| 46 |
+
"sym": null
|
| 47 |
+
},
|
| 48 |
+
"model.layers.1.mlp.gate": {
|
| 49 |
+
"bits": 32,
|
| 50 |
+
"data_type": "bfloat",
|
| 51 |
+
"group_size": null,
|
| 52 |
+
"sym": null
|
| 53 |
+
},
|
| 54 |
+
"model.layers.1.mlp.shared_expert_gate": {
|
| 55 |
+
"bits": 32,
|
| 56 |
+
"data_type": "bfloat",
|
| 57 |
+
"group_size": null,
|
| 58 |
+
"sym": null
|
| 59 |
+
},
|
| 60 |
+
"model.layers.10.mlp.gate": {
|
| 61 |
+
"bits": 32,
|
| 62 |
+
"data_type": "bfloat",
|
| 63 |
+
"group_size": null,
|
| 64 |
+
"sym": null
|
| 65 |
+
},
|
| 66 |
+
"model.layers.10.mlp.shared_expert_gate": {
|
| 67 |
+
"bits": 32,
|
| 68 |
+
"data_type": "bfloat",
|
| 69 |
+
"group_size": null,
|
| 70 |
+
"sym": null
|
| 71 |
+
},
|
| 72 |
+
"model.layers.11.mlp.gate": {
|
| 73 |
+
"bits": 32,
|
| 74 |
+
"data_type": "bfloat",
|
| 75 |
+
"group_size": null,
|
| 76 |
+
"sym": null
|
| 77 |
+
},
|
| 78 |
+
"model.layers.11.mlp.shared_expert_gate": {
|
| 79 |
+
"bits": 32,
|
| 80 |
+
"data_type": "bfloat",
|
| 81 |
+
"group_size": null,
|
| 82 |
+
"sym": null
|
| 83 |
+
},
|
| 84 |
+
"model.layers.12.mlp.gate": {
|
| 85 |
+
"bits": 32,
|
| 86 |
+
"data_type": "bfloat",
|
| 87 |
+
"group_size": null,
|
| 88 |
+
"sym": null
|
| 89 |
+
},
|
| 90 |
+
"model.layers.12.mlp.shared_expert_gate": {
|
| 91 |
+
"bits": 32,
|
| 92 |
+
"data_type": "bfloat",
|
| 93 |
+
"group_size": null,
|
| 94 |
+
"sym": null
|
| 95 |
+
},
|
| 96 |
+
"model.layers.13.mlp.gate": {
|
| 97 |
+
"bits": 32,
|
| 98 |
+
"data_type": "bfloat",
|
| 99 |
+
"group_size": null,
|
| 100 |
+
"sym": null
|
| 101 |
+
},
|
| 102 |
+
"model.layers.13.mlp.shared_expert_gate": {
|
| 103 |
+
"bits": 32,
|
| 104 |
+
"data_type": "bfloat",
|
| 105 |
+
"group_size": null,
|
| 106 |
+
"sym": null
|
| 107 |
+
},
|
| 108 |
+
"model.layers.14.mlp.gate": {
|
| 109 |
+
"bits": 32,
|
| 110 |
+
"data_type": "bfloat",
|
| 111 |
+
"group_size": null,
|
| 112 |
+
"sym": null
|
| 113 |
+
},
|
| 114 |
+
"model.layers.14.mlp.shared_expert_gate": {
|
| 115 |
+
"bits": 32,
|
| 116 |
+
"data_type": "bfloat",
|
| 117 |
+
"group_size": null,
|
| 118 |
+
"sym": null
|
| 119 |
+
},
|
| 120 |
+
"model.layers.15.mlp.gate": {
|
| 121 |
+
"bits": 32,
|
| 122 |
+
"data_type": "bfloat",
|
| 123 |
+
"group_size": null,
|
| 124 |
+
"sym": null
|
| 125 |
+
},
|
| 126 |
+
"model.layers.15.mlp.shared_expert_gate": {
|
| 127 |
+
"bits": 32,
|
| 128 |
+
"data_type": "bfloat",
|
| 129 |
+
"group_size": null,
|
| 130 |
+
"sym": null
|
| 131 |
+
},
|
| 132 |
+
"model.layers.16.mlp.gate": {
|
| 133 |
+
"bits": 32,
|
| 134 |
+
"data_type": "bfloat",
|
| 135 |
+
"group_size": null,
|
| 136 |
+
"sym": null
|
| 137 |
+
},
|
| 138 |
+
"model.layers.16.mlp.shared_expert_gate": {
|
| 139 |
+
"bits": 32,
|
| 140 |
+
"data_type": "bfloat",
|
| 141 |
+
"group_size": null,
|
| 142 |
+
"sym": null
|
| 143 |
+
},
|
| 144 |
+
"model.layers.17.mlp.gate": {
|
| 145 |
+
"bits": 32,
|
| 146 |
+
"data_type": "bfloat",
|
| 147 |
+
"group_size": null,
|
| 148 |
+
"sym": null
|
| 149 |
+
},
|
| 150 |
+
"model.layers.17.mlp.shared_expert_gate": {
|
| 151 |
+
"bits": 32,
|
| 152 |
+
"data_type": "bfloat",
|
| 153 |
+
"group_size": null,
|
| 154 |
+
"sym": null
|
| 155 |
+
},
|
| 156 |
+
"model.layers.18.mlp.gate": {
|
| 157 |
+
"bits": 32,
|
| 158 |
+
"data_type": "bfloat",
|
| 159 |
+
"group_size": null,
|
| 160 |
+
"sym": null
|
| 161 |
+
},
|
| 162 |
+
"model.layers.18.mlp.shared_expert_gate": {
|
| 163 |
+
"bits": 32,
|
| 164 |
+
"data_type": "bfloat",
|
| 165 |
+
"group_size": null,
|
| 166 |
+
"sym": null
|
| 167 |
+
},
|
| 168 |
+
"model.layers.19.mlp.gate": {
|
| 169 |
+
"bits": 32,
|
| 170 |
+
"data_type": "bfloat",
|
| 171 |
+
"group_size": null,
|
| 172 |
+
"sym": null
|
| 173 |
+
},
|
| 174 |
+
"model.layers.19.mlp.shared_expert_gate": {
|
| 175 |
+
"bits": 32,
|
| 176 |
+
"data_type": "bfloat",
|
| 177 |
+
"group_size": null,
|
| 178 |
+
"sym": null
|
| 179 |
+
},
|
| 180 |
+
"model.layers.2.mlp.gate": {
|
| 181 |
+
"bits": 32,
|
| 182 |
+
"data_type": "bfloat",
|
| 183 |
+
"group_size": null,
|
| 184 |
+
"sym": null
|
| 185 |
+
},
|
| 186 |
+
"model.layers.2.mlp.shared_expert_gate": {
|
| 187 |
+
"bits": 32,
|
| 188 |
+
"data_type": "bfloat",
|
| 189 |
+
"group_size": null,
|
| 190 |
+
"sym": null
|
| 191 |
+
},
|
| 192 |
+
"model.layers.20.mlp.gate": {
|
| 193 |
+
"bits": 32,
|
| 194 |
+
"data_type": "bfloat",
|
| 195 |
+
"group_size": null,
|
| 196 |
+
"sym": null
|
| 197 |
+
},
|
| 198 |
+
"model.layers.20.mlp.shared_expert_gate": {
|
| 199 |
+
"bits": 32,
|
| 200 |
+
"data_type": "bfloat",
|
| 201 |
+
"group_size": null,
|
| 202 |
+
"sym": null
|
| 203 |
+
},
|
| 204 |
+
"model.layers.21.mlp.gate": {
|
| 205 |
+
"bits": 32,
|
| 206 |
+
"data_type": "bfloat",
|
| 207 |
+
"group_size": null,
|
| 208 |
+
"sym": null
|
| 209 |
+
},
|
| 210 |
+
"model.layers.21.mlp.shared_expert_gate": {
|
| 211 |
+
"bits": 32,
|
| 212 |
+
"data_type": "bfloat",
|
| 213 |
+
"group_size": null,
|
| 214 |
+
"sym": null
|
| 215 |
+
},
|
| 216 |
+
"model.layers.22.mlp.gate": {
|
| 217 |
+
"bits": 32,
|
| 218 |
+
"data_type": "bfloat",
|
| 219 |
+
"group_size": null,
|
| 220 |
+
"sym": null
|
| 221 |
+
},
|
| 222 |
+
"model.layers.22.mlp.shared_expert_gate": {
|
| 223 |
+
"bits": 32,
|
| 224 |
+
"data_type": "bfloat",
|
| 225 |
+
"group_size": null,
|
| 226 |
+
"sym": null
|
| 227 |
+
},
|
| 228 |
+
"model.layers.23.mlp.gate": {
|
| 229 |
+
"bits": 32,
|
| 230 |
+
"data_type": "bfloat",
|
| 231 |
+
"group_size": null,
|
| 232 |
+
"sym": null
|
| 233 |
+
},
|
| 234 |
+
"model.layers.23.mlp.shared_expert_gate": {
|
| 235 |
+
"bits": 32,
|
| 236 |
+
"data_type": "bfloat",
|
| 237 |
+
"group_size": null,
|
| 238 |
+
"sym": null
|
| 239 |
+
},
|
| 240 |
+
"model.layers.24.mlp.gate": {
|
| 241 |
+
"bits": 32,
|
| 242 |
+
"data_type": "bfloat",
|
| 243 |
+
"group_size": null,
|
| 244 |
+
"sym": null
|
| 245 |
+
},
|
| 246 |
+
"model.layers.24.mlp.shared_expert_gate": {
|
| 247 |
+
"bits": 32,
|
| 248 |
+
"data_type": "bfloat",
|
| 249 |
+
"group_size": null,
|
| 250 |
+
"sym": null
|
| 251 |
+
},
|
| 252 |
+
"model.layers.25.mlp.gate": {
|
| 253 |
+
"bits": 32,
|
| 254 |
+
"data_type": "bfloat",
|
| 255 |
+
"group_size": null,
|
| 256 |
+
"sym": null
|
| 257 |
+
},
|
| 258 |
+
"model.layers.25.mlp.shared_expert_gate": {
|
| 259 |
+
"bits": 32,
|
| 260 |
+
"data_type": "bfloat",
|
| 261 |
+
"group_size": null,
|
| 262 |
+
"sym": null
|
| 263 |
+
},
|
| 264 |
+
"model.layers.26.mlp.gate": {
|
| 265 |
+
"bits": 32,
|
| 266 |
+
"data_type": "bfloat",
|
| 267 |
+
"group_size": null,
|
| 268 |
+
"sym": null
|
| 269 |
+
},
|
| 270 |
+
"model.layers.26.mlp.shared_expert_gate": {
|
| 271 |
+
"bits": 32,
|
| 272 |
+
"data_type": "bfloat",
|
| 273 |
+
"group_size": null,
|
| 274 |
+
"sym": null
|
| 275 |
+
},
|
| 276 |
+
"model.layers.27.mlp.gate": {
|
| 277 |
+
"bits": 32,
|
| 278 |
+
"data_type": "bfloat",
|
| 279 |
+
"group_size": null,
|
| 280 |
+
"sym": null
|
| 281 |
+
},
|
| 282 |
+
"model.layers.27.mlp.shared_expert_gate": {
|
| 283 |
+
"bits": 32,
|
| 284 |
+
"data_type": "bfloat",
|
| 285 |
+
"group_size": null,
|
| 286 |
+
"sym": null
|
| 287 |
+
},
|
| 288 |
+
"model.layers.3.mlp.gate": {
|
| 289 |
+
"bits": 32,
|
| 290 |
+
"data_type": "bfloat",
|
| 291 |
+
"group_size": null,
|
| 292 |
+
"sym": null
|
| 293 |
+
},
|
| 294 |
+
"model.layers.3.mlp.shared_expert_gate": {
|
| 295 |
+
"bits": 32,
|
| 296 |
+
"data_type": "bfloat",
|
| 297 |
+
"group_size": null,
|
| 298 |
+
"sym": null
|
| 299 |
+
},
|
| 300 |
+
"model.layers.4.mlp.gate": {
|
| 301 |
+
"bits": 32,
|
| 302 |
+
"data_type": "bfloat",
|
| 303 |
+
"group_size": null,
|
| 304 |
+
"sym": null
|
| 305 |
+
},
|
| 306 |
+
"model.layers.4.mlp.shared_expert_gate": {
|
| 307 |
+
"bits": 32,
|
| 308 |
+
"data_type": "bfloat",
|
| 309 |
+
"group_size": null,
|
| 310 |
+
"sym": null
|
| 311 |
+
},
|
| 312 |
+
"model.layers.5.mlp.gate": {
|
| 313 |
+
"bits": 32,
|
| 314 |
+
"data_type": "bfloat",
|
| 315 |
+
"group_size": null,
|
| 316 |
+
"sym": null
|
| 317 |
+
},
|
| 318 |
+
"model.layers.5.mlp.shared_expert_gate": {
|
| 319 |
+
"bits": 32,
|
| 320 |
+
"data_type": "bfloat",
|
| 321 |
+
"group_size": null,
|
| 322 |
+
"sym": null
|
| 323 |
+
},
|
| 324 |
+
"model.layers.6.mlp.gate": {
|
| 325 |
+
"bits": 32,
|
| 326 |
+
"data_type": "bfloat",
|
| 327 |
+
"group_size": null,
|
| 328 |
+
"sym": null
|
| 329 |
+
},
|
| 330 |
+
"model.layers.6.mlp.shared_expert_gate": {
|
| 331 |
+
"bits": 32,
|
| 332 |
+
"data_type": "bfloat",
|
| 333 |
+
"group_size": null,
|
| 334 |
+
"sym": null
|
| 335 |
+
},
|
| 336 |
+
"model.layers.7.mlp.gate": {
|
| 337 |
+
"bits": 32,
|
| 338 |
+
"data_type": "bfloat",
|
| 339 |
+
"group_size": null,
|
| 340 |
+
"sym": null
|
| 341 |
+
},
|
| 342 |
+
"model.layers.7.mlp.shared_expert_gate": {
|
| 343 |
+
"bits": 32,
|
| 344 |
+
"data_type": "bfloat",
|
| 345 |
+
"group_size": null,
|
| 346 |
+
"sym": null
|
| 347 |
+
},
|
| 348 |
+
"model.layers.8.mlp.gate": {
|
| 349 |
+
"bits": 32,
|
| 350 |
+
"data_type": "bfloat",
|
| 351 |
+
"group_size": null,
|
| 352 |
+
"sym": null
|
| 353 |
+
},
|
| 354 |
+
"model.layers.8.mlp.shared_expert_gate": {
|
| 355 |
+
"bits": 32,
|
| 356 |
+
"data_type": "bfloat",
|
| 357 |
+
"group_size": null,
|
| 358 |
+
"sym": null
|
| 359 |
+
},
|
| 360 |
+
"model.layers.9.mlp.gate": {
|
| 361 |
+
"bits": 32,
|
| 362 |
+
"data_type": "bfloat",
|
| 363 |
+
"group_size": null,
|
| 364 |
+
"sym": null
|
| 365 |
+
},
|
| 366 |
+
"model.layers.9.mlp.shared_expert_gate": {
|
| 367 |
+
"bits": 32,
|
| 368 |
+
"data_type": "bfloat",
|
| 369 |
+
"group_size": null,
|
| 370 |
+
"sym": null
|
| 371 |
+
}
|
| 372 |
+
},
|
| 373 |
+
"gradient_accumulate_steps": 1,
|
| 374 |
+
"group_size": 128,
|
| 375 |
+
"iters": 1000,
|
| 376 |
+
"low_gpu_mem_usage": false,
|
| 377 |
+
"lr": 0.001,
|
| 378 |
+
"minmax_lr": 0.001,
|
| 379 |
+
"nsamples": 512,
|
| 380 |
+
"quant_method": "intel/auto-round",
|
| 381 |
+
"scale_dtype": "torch.float16",
|
| 382 |
+
"seqlen": 2048,
|
| 383 |
+
"sym": false,
|
| 384 |
+
"train_bs": 8
|
| 385 |
+
},
|
| 386 |
+
"rms_norm_eps": 1e-06,
|
| 387 |
+
"rope_theta": 1000000.0,
|
| 388 |
+
"router_aux_loss_coef": 0.001,
|
| 389 |
+
"shared_expert_intermediate_size": 20480,
|
| 390 |
+
"sliding_window": 65536,
|
| 391 |
+
"tie_word_embeddings": false,
|
| 392 |
+
"torch_dtype": "bfloat16",
|
| 393 |
+
"transformers_version": "4.41.1",
|
| 394 |
+
"use_cache": true,
|
| 395 |
+
"use_sliding_window": false,
|
| 396 |
+
"vocab_size": 151936
|
| 397 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.41.1"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167fc297862ecd2e0033de4c717668a83a6904b31c14025c6d96298f08706e4b
|
| 3 |
+
size 4999673648
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e484a47e41edba04660cf6862d0ee5c2cb1d8614968c35b5ec7aa1cbe7681b3
|
| 3 |
+
size 4996756752
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77db3c5e4a435e4f834011974388b3f8d177e83537c5acd5764d06db3c592462
|
| 3 |
+
size 4996759400
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74f499b3d5cc607ee82042f2de2bc4ace38bd51e0b947b702ac52b39e91563b8
|
| 3 |
+
size 4996760664
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c825fa9b74f5e7f55362b085315c8db3c82e4679e0faae23c07eb1ffff8eed3c
|
| 3 |
+
size 5000290584
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79105d05c0ea1507176ced998d5598cb3b4f4a7678abea09d87cd87e682120b6
|
| 3 |
+
size 4996760576
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d6e7a53c719cb3c8938fbaad0e638d1f5149a40bcc3103539004ef994eb072
|
| 3 |
+
size 1538228952
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantization_config.json
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"sym": false,
|
| 5 |
+
"data_type": "int",
|
| 6 |
+
"enable_quanted_input": true,
|
| 7 |
+
"enable_minmax_tuning": true,
|
| 8 |
+
"seqlen": 2048,
|
| 9 |
+
"train_bs": 8,
|
| 10 |
+
"scale_dtype": "torch.float16",
|
| 11 |
+
"lr": 0.001,
|
| 12 |
+
"minmax_lr": 0.001,
|
| 13 |
+
"gradient_accumulate_steps": 1,
|
| 14 |
+
"iters": 1000,
|
| 15 |
+
"amp": true,
|
| 16 |
+
"nsamples": 512,
|
| 17 |
+
"low_gpu_mem_usage": false,
|
| 18 |
+
"dataset": "NeelNanda/pile-10k",
|
| 19 |
+
"autoround_version": "0.3.0.dev",
|
| 20 |
+
"quant_method": "intel/auto-round",
|
| 21 |
+
"backend": "auto_round:exllamav2",
|
| 22 |
+
"extra_config": {
|
| 23 |
+
"model.layers.0.mlp.shared_expert_gate": {
|
| 24 |
+
"data_type": "bfloat",
|
| 25 |
+
"bits": 32,
|
| 26 |
+
"group_size": null,
|
| 27 |
+
"sym": null
|
| 28 |
+
},
|
| 29 |
+
"model.layers.1.mlp.shared_expert_gate": {
|
| 30 |
+
"data_type": "bfloat",
|
| 31 |
+
"bits": 32,
|
| 32 |
+
"group_size": null,
|
| 33 |
+
"sym": null
|
| 34 |
+
},
|
| 35 |
+
"model.layers.2.mlp.shared_expert_gate": {
|
| 36 |
+
"data_type": "bfloat",
|
| 37 |
+
"bits": 32,
|
| 38 |
+
"group_size": null,
|
| 39 |
+
"sym": null
|
| 40 |
+
},
|
| 41 |
+
"model.layers.3.mlp.shared_expert_gate": {
|
| 42 |
+
"data_type": "bfloat",
|
| 43 |
+
"bits": 32,
|
| 44 |
+
"group_size": null,
|
| 45 |
+
"sym": null
|
| 46 |
+
},
|
| 47 |
+
"model.layers.4.mlp.shared_expert_gate": {
|
| 48 |
+
"data_type": "bfloat",
|
| 49 |
+
"bits": 32,
|
| 50 |
+
"group_size": null,
|
| 51 |
+
"sym": null
|
| 52 |
+
},
|
| 53 |
+
"model.layers.5.mlp.shared_expert_gate": {
|
| 54 |
+
"data_type": "bfloat",
|
| 55 |
+
"bits": 32,
|
| 56 |
+
"group_size": null,
|
| 57 |
+
"sym": null
|
| 58 |
+
},
|
| 59 |
+
"model.layers.6.mlp.shared_expert_gate": {
|
| 60 |
+
"data_type": "bfloat",
|
| 61 |
+
"bits": 32,
|
| 62 |
+
"group_size": null,
|
| 63 |
+
"sym": null
|
| 64 |
+
},
|
| 65 |
+
"model.layers.7.mlp.shared_expert_gate": {
|
| 66 |
+
"data_type": "bfloat",
|
| 67 |
+
"bits": 32,
|
| 68 |
+
"group_size": null,
|
| 69 |
+
"sym": null
|
| 70 |
+
},
|
| 71 |
+
"model.layers.8.mlp.shared_expert_gate": {
|
| 72 |
+
"data_type": "bfloat",
|
| 73 |
+
"bits": 32,
|
| 74 |
+
"group_size": null,
|
| 75 |
+
"sym": null
|
| 76 |
+
},
|
| 77 |
+
"model.layers.9.mlp.shared_expert_gate": {
|
| 78 |
+
"data_type": "bfloat",
|
| 79 |
+
"bits": 32,
|
| 80 |
+
"group_size": null,
|
| 81 |
+
"sym": null
|
| 82 |
+
},
|
| 83 |
+
"model.layers.10.mlp.shared_expert_gate": {
|
| 84 |
+
"data_type": "bfloat",
|
| 85 |
+
"bits": 32,
|
| 86 |
+
"group_size": null,
|
| 87 |
+
"sym": null
|
| 88 |
+
},
|
| 89 |
+
"model.layers.11.mlp.shared_expert_gate": {
|
| 90 |
+
"data_type": "bfloat",
|
| 91 |
+
"bits": 32,
|
| 92 |
+
"group_size": null,
|
| 93 |
+
"sym": null
|
| 94 |
+
},
|
| 95 |
+
"model.layers.12.mlp.shared_expert_gate": {
|
| 96 |
+
"data_type": "bfloat",
|
| 97 |
+
"bits": 32,
|
| 98 |
+
"group_size": null,
|
| 99 |
+
"sym": null
|
| 100 |
+
},
|
| 101 |
+
"model.layers.13.mlp.shared_expert_gate": {
|
| 102 |
+
"data_type": "bfloat",
|
| 103 |
+
"bits": 32,
|
| 104 |
+
"group_size": null,
|
| 105 |
+
"sym": null
|
| 106 |
+
},
|
| 107 |
+
"model.layers.14.mlp.shared_expert_gate": {
|
| 108 |
+
"data_type": "bfloat",
|
| 109 |
+
"bits": 32,
|
| 110 |
+
"group_size": null,
|
| 111 |
+
"sym": null
|
| 112 |
+
},
|
| 113 |
+
"model.layers.15.mlp.shared_expert_gate": {
|
| 114 |
+
"data_type": "bfloat",
|
| 115 |
+
"bits": 32,
|
| 116 |
+
"group_size": null,
|
| 117 |
+
"sym": null
|
| 118 |
+
},
|
| 119 |
+
"model.layers.16.mlp.shared_expert_gate": {
|
| 120 |
+
"data_type": "bfloat",
|
| 121 |
+
"bits": 32,
|
| 122 |
+
"group_size": null,
|
| 123 |
+
"sym": null
|
| 124 |
+
},
|
| 125 |
+
"model.layers.17.mlp.shared_expert_gate": {
|
| 126 |
+
"data_type": "bfloat",
|
| 127 |
+
"bits": 32,
|
| 128 |
+
"group_size": null,
|
| 129 |
+
"sym": null
|
| 130 |
+
},
|
| 131 |
+
"model.layers.18.mlp.shared_expert_gate": {
|
| 132 |
+
"data_type": "bfloat",
|
| 133 |
+
"bits": 32,
|
| 134 |
+
"group_size": null,
|
| 135 |
+
"sym": null
|
| 136 |
+
},
|
| 137 |
+
"model.layers.19.mlp.shared_expert_gate": {
|
| 138 |
+
"data_type": "bfloat",
|
| 139 |
+
"bits": 32,
|
| 140 |
+
"group_size": null,
|
| 141 |
+
"sym": null
|
| 142 |
+
},
|
| 143 |
+
"model.layers.20.mlp.shared_expert_gate": {
|
| 144 |
+
"data_type": "bfloat",
|
| 145 |
+
"bits": 32,
|
| 146 |
+
"group_size": null,
|
| 147 |
+
"sym": null
|
| 148 |
+
},
|
| 149 |
+
"model.layers.21.mlp.shared_expert_gate": {
|
| 150 |
+
"data_type": "bfloat",
|
| 151 |
+
"bits": 32,
|
| 152 |
+
"group_size": null,
|
| 153 |
+
"sym": null
|
| 154 |
+
},
|
| 155 |
+
"model.layers.22.mlp.shared_expert_gate": {
|
| 156 |
+
"data_type": "bfloat",
|
| 157 |
+
"bits": 32,
|
| 158 |
+
"group_size": null,
|
| 159 |
+
"sym": null
|
| 160 |
+
},
|
| 161 |
+
"model.layers.23.mlp.shared_expert_gate": {
|
| 162 |
+
"data_type": "bfloat",
|
| 163 |
+
"bits": 32,
|
| 164 |
+
"group_size": null,
|
| 165 |
+
"sym": null
|
| 166 |
+
},
|
| 167 |
+
"model.layers.24.mlp.shared_expert_gate": {
|
| 168 |
+
"data_type": "bfloat",
|
| 169 |
+
"bits": 32,
|
| 170 |
+
"group_size": null,
|
| 171 |
+
"sym": null
|
| 172 |
+
},
|
| 173 |
+
"model.layers.25.mlp.shared_expert_gate": {
|
| 174 |
+
"data_type": "bfloat",
|
| 175 |
+
"bits": 32,
|
| 176 |
+
"group_size": null,
|
| 177 |
+
"sym": null
|
| 178 |
+
},
|
| 179 |
+
"model.layers.26.mlp.shared_expert_gate": {
|
| 180 |
+
"data_type": "bfloat",
|
| 181 |
+
"bits": 32,
|
| 182 |
+
"group_size": null,
|
| 183 |
+
"sym": null
|
| 184 |
+
},
|
| 185 |
+
"model.layers.27.mlp.shared_expert_gate": {
|
| 186 |
+
"data_type": "bfloat",
|
| 187 |
+
"bits": 32,
|
| 188 |
+
"group_size": null,
|
| 189 |
+
"sym": null
|
| 190 |
+
},
|
| 191 |
+
"model.layers.0.mlp.gate": {
|
| 192 |
+
"data_type": "bfloat",
|
| 193 |
+
"bits": 32,
|
| 194 |
+
"group_size": null,
|
| 195 |
+
"sym": null
|
| 196 |
+
},
|
| 197 |
+
"model.layers.1.mlp.gate": {
|
| 198 |
+
"data_type": "bfloat",
|
| 199 |
+
"bits": 32,
|
| 200 |
+
"group_size": null,
|
| 201 |
+
"sym": null
|
| 202 |
+
},
|
| 203 |
+
"model.layers.2.mlp.gate": {
|
| 204 |
+
"data_type": "bfloat",
|
| 205 |
+
"bits": 32,
|
| 206 |
+
"group_size": null,
|
| 207 |
+
"sym": null
|
| 208 |
+
},
|
| 209 |
+
"model.layers.3.mlp.gate": {
|
| 210 |
+
"data_type": "bfloat",
|
| 211 |
+
"bits": 32,
|
| 212 |
+
"group_size": null,
|
| 213 |
+
"sym": null
|
| 214 |
+
},
|
| 215 |
+
"model.layers.4.mlp.gate": {
|
| 216 |
+
"data_type": "bfloat",
|
| 217 |
+
"bits": 32,
|
| 218 |
+
"group_size": null,
|
| 219 |
+
"sym": null
|
| 220 |
+
},
|
| 221 |
+
"model.layers.5.mlp.gate": {
|
| 222 |
+
"data_type": "bfloat",
|
| 223 |
+
"bits": 32,
|
| 224 |
+
"group_size": null,
|
| 225 |
+
"sym": null
|
| 226 |
+
},
|
| 227 |
+
"model.layers.6.mlp.gate": {
|
| 228 |
+
"data_type": "bfloat",
|
| 229 |
+
"bits": 32,
|
| 230 |
+
"group_size": null,
|
| 231 |
+
"sym": null
|
| 232 |
+
},
|
| 233 |
+
"model.layers.7.mlp.gate": {
|
| 234 |
+
"data_type": "bfloat",
|
| 235 |
+
"bits": 32,
|
| 236 |
+
"group_size": null,
|
| 237 |
+
"sym": null
|
| 238 |
+
},
|
| 239 |
+
"model.layers.8.mlp.gate": {
|
| 240 |
+
"data_type": "bfloat",
|
| 241 |
+
"bits": 32,
|
| 242 |
+
"group_size": null,
|
| 243 |
+
"sym": null
|
| 244 |
+
},
|
| 245 |
+
"model.layers.9.mlp.gate": {
|
| 246 |
+
"data_type": "bfloat",
|
| 247 |
+
"bits": 32,
|
| 248 |
+
"group_size": null,
|
| 249 |
+
"sym": null
|
| 250 |
+
},
|
| 251 |
+
"model.layers.10.mlp.gate": {
|
| 252 |
+
"data_type": "bfloat",
|
| 253 |
+
"bits": 32,
|
| 254 |
+
"group_size": null,
|
| 255 |
+
"sym": null
|
| 256 |
+
},
|
| 257 |
+
"model.layers.11.mlp.gate": {
|
| 258 |
+
"data_type": "bfloat",
|
| 259 |
+
"bits": 32,
|
| 260 |
+
"group_size": null,
|
| 261 |
+
"sym": null
|
| 262 |
+
},
|
| 263 |
+
"model.layers.12.mlp.gate": {
|
| 264 |
+
"data_type": "bfloat",
|
| 265 |
+
"bits": 32,
|
| 266 |
+
"group_size": null,
|
| 267 |
+
"sym": null
|
| 268 |
+
},
|
| 269 |
+
"model.layers.13.mlp.gate": {
|
| 270 |
+
"data_type": "bfloat",
|
| 271 |
+
"bits": 32,
|
| 272 |
+
"group_size": null,
|
| 273 |
+
"sym": null
|
| 274 |
+
},
|
| 275 |
+
"model.layers.14.mlp.gate": {
|
| 276 |
+
"data_type": "bfloat",
|
| 277 |
+
"bits": 32,
|
| 278 |
+
"group_size": null,
|
| 279 |
+
"sym": null
|
| 280 |
+
},
|
| 281 |
+
"model.layers.15.mlp.gate": {
|
| 282 |
+
"data_type": "bfloat",
|
| 283 |
+
"bits": 32,
|
| 284 |
+
"group_size": null,
|
| 285 |
+
"sym": null
|
| 286 |
+
},
|
| 287 |
+
"model.layers.16.mlp.gate": {
|
| 288 |
+
"data_type": "bfloat",
|
| 289 |
+
"bits": 32,
|
| 290 |
+
"group_size": null,
|
| 291 |
+
"sym": null
|
| 292 |
+
},
|
| 293 |
+
"model.layers.17.mlp.gate": {
|
| 294 |
+
"data_type": "bfloat",
|
| 295 |
+
"bits": 32,
|
| 296 |
+
"group_size": null,
|
| 297 |
+
"sym": null
|
| 298 |
+
},
|
| 299 |
+
"model.layers.18.mlp.gate": {
|
| 300 |
+
"data_type": "bfloat",
|
| 301 |
+
"bits": 32,
|
| 302 |
+
"group_size": null,
|
| 303 |
+
"sym": null
|
| 304 |
+
},
|
| 305 |
+
"model.layers.19.mlp.gate": {
|
| 306 |
+
"data_type": "bfloat",
|
| 307 |
+
"bits": 32,
|
| 308 |
+
"group_size": null,
|
| 309 |
+
"sym": null
|
| 310 |
+
},
|
| 311 |
+
"model.layers.20.mlp.gate": {
|
| 312 |
+
"data_type": "bfloat",
|
| 313 |
+
"bits": 32,
|
| 314 |
+
"group_size": null,
|
| 315 |
+
"sym": null
|
| 316 |
+
},
|
| 317 |
+
"model.layers.21.mlp.gate": {
|
| 318 |
+
"data_type": "bfloat",
|
| 319 |
+
"bits": 32,
|
| 320 |
+
"group_size": null,
|
| 321 |
+
"sym": null
|
| 322 |
+
},
|
| 323 |
+
"model.layers.22.mlp.gate": {
|
| 324 |
+
"data_type": "bfloat",
|
| 325 |
+
"bits": 32,
|
| 326 |
+
"group_size": null,
|
| 327 |
+
"sym": null
|
| 328 |
+
},
|
| 329 |
+
"model.layers.23.mlp.gate": {
|
| 330 |
+
"data_type": "bfloat",
|
| 331 |
+
"bits": 32,
|
| 332 |
+
"group_size": null,
|
| 333 |
+
"sym": null
|
| 334 |
+
},
|
| 335 |
+
"model.layers.24.mlp.gate": {
|
| 336 |
+
"data_type": "bfloat",
|
| 337 |
+
"bits": 32,
|
| 338 |
+
"group_size": null,
|
| 339 |
+
"sym": null
|
| 340 |
+
},
|
| 341 |
+
"model.layers.25.mlp.gate": {
|
| 342 |
+
"data_type": "bfloat",
|
| 343 |
+
"bits": 32,
|
| 344 |
+
"group_size": null,
|
| 345 |
+
"sym": null
|
| 346 |
+
},
|
| 347 |
+
"model.layers.26.mlp.gate": {
|
| 348 |
+
"data_type": "bfloat",
|
| 349 |
+
"bits": 32,
|
| 350 |
+
"group_size": null,
|
| 351 |
+
"sym": null
|
| 352 |
+
},
|
| 353 |
+
"model.layers.27.mlp.gate": {
|
| 354 |
+
"data_type": "bfloat",
|
| 355 |
+
"bits": 32,
|
| 356 |
+
"group_size": null,
|
| 357 |
+
"sym": null
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 65536,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|