File size: 97,250 Bytes
ce4ecd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 |
/usr/bin/python3 -m mlc_llm gen_config dist/models/stablelm-2-zephyr-1_6b --quantization q4f32_1 --conv-template stablelm-2 --output /tmp/tmpt74_sq0w --context-window-size 4096
[2024-05-24 18:29:33] INFO auto_config.py:115: [92mFound[0m model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
[2024-05-24 18:29:33] INFO auto_config.py:153: [92mFound[0m model type: [1mstablelm[0m. Use `--model-type` to override.
[2024-05-24 18:29:33] INFO stablelm_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-05-24 18:29:33] INFO stablelm_model.py:66: [1mprefill_chunk_size[0m defaults to 2048
[2024-05-24 18:29:33] INFO config.py:106: Overriding [1mcontext_window_size[0m from 4096 to 4096
[2024-05-24 18:29:33] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
[2024-05-24 18:29:33] INFO gen_config.py:255: [generation_config.json] Setting [1mbos_token_id[0m: 100257
[2024-05-24 18:29:33] INFO gen_config.py:255: [generation_config.json] Setting [1meos_token_id[0m: 100257
[2024-05-24 18:29:33] INFO gen_config.py:269: [91mNot found[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.model
[2024-05-24 18:29:33] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer.json. Copying to [1m/tmp/tmpt74_sq0w/tokenizer.json[0m
[2024-05-24 18:29:33] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/vocab.json. Copying to [1m/tmp/tmpt74_sq0w/vocab.json[0m
[2024-05-24 18:29:33] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/merges.txt. Copying to [1m/tmp/tmpt74_sq0w/merges.txt[0m
[2024-05-24 18:29:33] INFO gen_config.py:269: [91mNot found[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/added_tokens.json
[2024-05-24 18:29:33] INFO gen_config.py:267: [92mFound[0m tokenizer config: dist/models/stablelm-2-zephyr-1_6b/tokenizer_config.json. Copying to [1m/tmp/tmpt74_sq0w/tokenizer_config.json[0m
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mpad_token_id[0m: 0
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mtemperature[0m: 0.7
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mpresence_penalty[0m: 0.0
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mfrequency_penalty[0m: 0.0
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mrepetition_penalty[0m: 1.0
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mtop_p[0m: 0.95
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mmean_gen_len[0m: 128
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mmax_gen_len[0m: 512
[2024-05-24 18:29:33] INFO gen_config.py:80: [System default] Setting [1mshift_fill_factor[0m: 0.3
[2024-05-24 18:29:33] INFO gen_config.py:335: Dumping configuration file to: [1m/tmp/tmpt74_sq0w/mlc-chat-config.json[0m
/usr/bin/python3 -m mlc_llm convert_weight dist/models/stablelm-2-zephyr-1_6b --quantization q4f32_1 --source-format auto --output /tmp/tmpt74_sq0w
[2024-05-24 18:29:34] INFO auto_config.py:115: [92mFound[0m model configuration: dist/models/stablelm-2-zephyr-1_6b/config.json
[2024-05-24 18:29:36] INFO auto_device.py:79: [92mFound[0m device: cuda:0
[2024-05-24 18:29:37] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
[2024-05-24 18:29:38] INFO auto_device.py:88: [91mNot found[0m device: metal:0
[2024-05-24 18:29:39] INFO auto_device.py:88: [91mNot found[0m device: vulkan:0
[2024-05-24 18:29:40] INFO auto_device.py:88: [91mNot found[0m device: opencl:0
[2024-05-24 18:29:40] INFO auto_device.py:35: Using device: [1mcuda:0[0m
[2024-05-24 18:29:40] INFO auto_weight.py:70: Finding weights in: dist/models/stablelm-2-zephyr-1_6b
[2024-05-24 18:29:40] INFO auto_weight.py:136: [91mNot found[0m Huggingface PyTorch
[2024-05-24 18:29:40] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
[2024-05-24 18:29:40] INFO auto_weight.py:106: Using source weight configuration: [1mdist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json[0m. Use `--source` to override.
[2024-05-24 18:29:40] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
[2024-05-24 18:29:40] INFO auto_config.py:153: [92mFound[0m model type: [1mstablelm[0m. Use `--model-type` to override.
[2024-05-24 18:29:40] INFO stablelm_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-05-24 18:29:40] INFO stablelm_model.py:66: [1mprefill_chunk_size[0m defaults to 2048
[1mWeight conversion with arguments:[0m
[1m--config[0m dist/models/stablelm-2-zephyr-1_6b/config.json
[1m--quantization[0m GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
[1m--model-type[0m stablelm
[1m--device[0m cuda:0
[1m--source[0m dist/models/stablelm-2-zephyr-1_6b/model.safetensors.index.json
[1m--source-format[0m huggingface-safetensor
[1m--output[0m /tmp/tmpt74_sq0w
Start storing to cache /tmp/tmpt74_sq0w
0%| | 0/220 [00:00<?, ?it/s]
[2024-05-24 18:29:43] INFO huggingface_loader.py:184: Loading HF parameters from: dist/models/stablelm-2-zephyr-1_6b/model.safetensors
0%| | 0/220 [00:00<?, ?it/s]
[2024-05-24 18:29:44] INFO group_quantization.py:217: Compiling quantize function for key: ((100352, 2048), float32, cuda, axis=1, output_transpose=False)
0%| | 0/220 [00:01<?, ?it/s]
[2024-05-24 18:29:46] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mlm_head.q_weight[0m", shape: (100352, 256), dtype: uint32
0%| | 0/220 [00:03<?, ?it/s]
[2024-05-24 18:29:46] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mlm_head.q_scale[0m", shape: (100352, 64), dtype: float32
0%| | 0/220 [00:03<?, ?it/s]/home/tlopex/.local/lib/python3.8/site-packages/numpy/core/getlimits.py:518: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
setattr(self, word, getattr(machar, word).flat[0])
/home/tlopex/.local/lib/python3.8/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
return self._float_to_str(self.smallest_subnormal)
0%| | 1/220 [00:03<12:53, 3.53s/it]
[2024-05-24 18:29:47] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.embed_tokens.q_weight[0m", shape: (100352, 256), dtype: uint32
0%| | 1/220 [00:04<12:53, 3.53s/it]
[2024-05-24 18:29:47] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.embed_tokens.q_scale[0m", shape: (100352, 64), dtype: float32
0%| | 1/220 [00:04<12:53, 3.53s/it]
1%| | 2/220 [00:04<07:50, 2.16s/it]
[2024-05-24 18:29:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.bias[0m", shape: (2048,), dtype: float32
1%| | 2/220 [00:04<07:50, 2.16s/it]
[2024-05-24 18:29:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float32
1%| | 2/220 [00:04<07:50, 2.16s/it]
[2024-05-24 18:29:47] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5632), float32, cuda, axis=1, output_transpose=False)
1%| | 2/220 [00:04<07:50, 2.16s/it]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
1%| | 2/220 [00:05<07:50, 2.16s/it]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
1%| | 2/220 [00:05<07:50, 2.16s/it]
2%|▏ | 5/220 [00:05<02:28, 1.45it/s]
[2024-05-24 18:29:48] INFO group_quantization.py:217: Compiling quantize function for key: ((11264, 2048), float32, cuda, axis=1, output_transpose=False)
2%|▏ | 5/220 [00:05<02:28, 1.45it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
2%|▏ | 5/220 [00:05<02:28, 1.45it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
2%|▏ | 5/220 [00:05<02:28, 1.45it/s]
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO group_quantization.py:217: Compiling quantize function for key: ((6144, 2048), float32, cuda, axis=1, output_transpose=False)
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
[2024-05-24 18:29:48] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
3%|▎ | 6/220 [00:05<02:09, 1.65it/s]
5%|▍ | 10/220 [00:05<01:00, 3.46it/s]
[2024-05-24 18:29:48] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 10/220 [00:05<01:00, 3.46it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
5%|▍ | 10/220 [00:05<01:00, 3.46it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
5%|▍ | 10/220 [00:05<01:00, 3.46it/s]
5%|▌ | 11/220 [00:05<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.bias[0m", shape: (2048,), dtype: float32
5%|▌ | 11/220 [00:05<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float32
5%|▌ | 11/220 [00:05<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
5%|▌ | 11/220 [00:05<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
5%|▌ | 11/220 [00:05<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
5%|▌ | 11/220 [00:06<00:59, 3.54it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
5%|▌ | 11/220 [00:06<00:59, 3.54it/s]
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.bias[0m", shape: (2048,), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
7%|▋ | 15/220 [00:06<00:32, 6.24it/s]
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.bias[0m", shape: (2048,), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
11%|█ | 24/220 [00:06<00:14, 13.50it/s]
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.bias[0m", shape: (2048,), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
15%|█▌ | 33/220 [00:06<00:09, 20.58it/s]
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.bias[0m", shape: (2048,), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
19%|█▉ | 42/220 [00:06<00:06, 27.17it/s]
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.bias[0m", shape: (2048,), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:49] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
23%|██▎ | 51/220 [00:06<00:05, 32.93it/s]
27%|██▋ | 60/220 [00:06<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
27%|██▋ | 60/220 [00:06<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
27%|██▋ | 60/220 [00:06<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
27%|██▋ | 60/220 [00:06<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.bias[0m", shape: (2048,), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
27%|██▋ | 60/220 [00:07<00:04, 37.69it/s]
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.bias[0m", shape: (2048,), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
31%|███▏ | 69/220 [00:07<00:03, 41.52it/s]
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.bias[0m", shape: (2048,), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
35%|███▌ | 78/220 [00:07<00:03, 44.44it/s]
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.bias[0m", shape: (2048,), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
40%|███▉ | 87/220 [00:07<00:02, 46.64it/s]
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.bias[0m", shape: (2048,), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
44%|████▎ | 96/220 [00:07<00:02, 48.27it/s]
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:50] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.bias[0m", shape: (2048,), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
48%|████▊ | 105/220 [00:07<00:02, 49.46it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
48%|████▊ | 105/220 [00:08<00:02, 49.46it/s]
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.bias[0m", shape: (2048,), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
52%|█████▏ | 114/220 [00:08<00:02, 50.30it/s]
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.bias[0m", shape: (2048,), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
56%|█████▌ | 123/220 [00:08<00:01, 50.90it/s]
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.bias[0m", shape: (2048,), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (2048,), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
60%|██████ | 132/220 [00:08<00:01, 51.32it/s]
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.bias[0m", shape: (2048,), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (2048,), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
64%|██████▍ | 141/220 [00:08<00:01, 51.60it/s]
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.bias[0m", shape: (2048,), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
[2024-05-24 18:29:51] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
68%|██████▊ | 150/220 [00:08<00:01, 51.82it/s]
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.bias[0m", shape: (2048,), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
72%|███████▏ | 159/220 [00:08<00:01, 51.97it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
72%|███████▏ | 159/220 [00:09<00:01, 51.97it/s]
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.bias[0m", shape: (2048,), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
76%|███████▋ | 168/220 [00:09<00:00, 52.08it/s]
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.bias[0m", shape: (2048,), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
80%|████████ | 177/220 [00:09<00:00, 52.14it/s]
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.bias[0m", shape: (2048,), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
85%|████████▍ | 186/220 [00:09<00:00, 52.23it/s]
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.bias[0m", shape: (2048,), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
89%|████████▊ | 195/220 [00:09<00:00, 52.25it/s]
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.bias[0m", shape: (2048,), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_weight[0m", shape: (2048, 704), dtype: uint32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.q_scale[0m", shape: (2048, 176), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:52] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_weight[0m", shape: (11264, 256), dtype: uint32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.q_scale[0m", shape: (11264, 64), dtype: float32
93%|█████████▎| 204/220 [00:09<00:00, 52.28it/s]
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.bias[0m", shape: (2048,), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.bias[0m", shape: (6144,), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_weight[0m", shape: (6144, 256), dtype: uint32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.q_scale[0m", shape: (6144, 64), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_weight[0m", shape: (2048, 256), dtype: uint32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:166: [Quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.q_scale[0m", shape: (2048, 64), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.norm.bias[0m", shape: (2048,), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float32
97%|█████████▋| 213/220 [00:09<00:00, 52.30it/s]
100%|██████████| 220/220 [00:09<00:00, 22.13it/s]
[2024-05-24 18:29:53] INFO huggingface_loader.py:196: Unloading HF weight file: dist/models/stablelm-2-zephyr-1_6b/model.safetensors
[2024-05-24 18:29:53] INFO stats.py:76: [92mTime usage[0m: HF loading: 1.007 sec; Pre-quantization mapping: 3.312 sec; Quantization: 2.344 sec
[2024-05-24 18:29:53] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 3.063 GB. Total bytes loaded from disk: 3.063 GB
[2024-05-24 18:29:53] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 0.958 GB
[2024-05-24 18:29:53] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,644,515,328
[2024-05-24 18:29:53] INFO convert_weight.py:161: [92mBits per parameter[0m: 5.006
[2024-05-24 18:29:53] INFO convert_weight.py:166: Saved to directory: [1m/tmp/tmpt74_sq0w[0m
All finished, 27 total shards committed, record saved to /tmp/tmpt74_sq0w/ndarray-cache.json
Also saved a bf16 record to /tmp/tmpt74_sq0w/ndarray-cache-b16.json
|