File size: 72,580 Bytes
3b0ced1 |
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 |
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Qwen2-1.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC [2024-06-06 23:39:30] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen2-1.5B-Instruct/config.json [2024-06-06 23:39:30] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. [2024-06-06 23:39:30] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) [2024-06-06 23:39:30] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 [2024-06-06 23:39:30] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 151643 [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 151643 [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [151645, 151643] [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mrepetition_penalty[0m: 1.1 [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mtemperature[0m: 0.7 [2024-06-06 23:39:30] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.8 [2024-06-06 23:39:30] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer.model [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer.json[0m [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/vocab.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/vocab.json[0m [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/merges.txt. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/merges.txt[0m [2024-06-06 23:39:30] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/Qwen2-1.5B-Instruct/added_tokens.json [2024-06-06 23:39:30] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/Qwen2-1.5B-Instruct/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer_config.json[0m [2024-06-06 23:39:30] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} [2024-06-06 23:39:30] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 [2024-06-06 23:39:30] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 [2024-06-06 23:39:30] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/mlc-chat-config.json[0m /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Qwen2-1.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC [2024-06-06 23:39:32] INFO auto_config.py:116: [92mFound[0m model configuration: /models/Qwen2-1.5B-Instruct/config.json [2024-06-06 23:39:33] INFO auto_device.py:79: [92mFound[0m device: cuda:0 [2024-06-06 23:39:35] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 [2024-06-06 23:39:36] INFO auto_device.py:88: [91mNot found[0m device: metal:0 [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 [2024-06-06 23:39:38] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 [2024-06-06 23:39:40] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 [2024-06-06 23:39:40] INFO auto_device.py:35: Using device: [1mcuda:0[0m [2024-06-06 23:39:40] INFO auto_weight.py:71: Finding weights in: /models/Qwen2-1.5B-Instruct [2024-06-06 23:39:40] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch [2024-06-06 23:39:40] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/Qwen2-1.5B-Instruct/model.safetensors.index.json [2024-06-06 23:39:40] INFO auto_weight.py:107: Using source weight configuration: [1m/models/Qwen2-1.5B-Instruct/model.safetensors.index.json[0m. Use `--source` to override. [2024-06-06 23:39:40] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. [2024-06-06 23:39:40] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. [2024-06-06 23:39:40] INFO qwen2_model.py:49: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) [2024-06-06 23:39:40] INFO qwen2_model.py:66: [1mprefill_chunk_size[0m defaults to 2048 Traceback (most recent call last): File "/opt/conda/envs/py310/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/opt/conda/envs/py310/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/__main__.py", line 64, in <module> main() File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/__main__.py", line 37, in main cli.main(sys.argv[2:]) File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/cli/convert_weight.py", line 88, in main convert_weight( File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 181, in convert_weight _convert_args(args) File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 145, in _convert_args tvmjs.dump_ndarray_cache( File "/opt/conda/envs/py310/lib/python3.10/site-packages/tvm/contrib/tvmjs.py", line 272, in dump_ndarray_cache for k, origin_v in param_generator: File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/interface/convert_weight.py", line 122, in _param_generator loader = LOADER[args.source_format]( File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/loader/huggingface_loader.py", line 99, in __init__ check_parameter_usage(extern_param_map, set(self.torch_to_path.keys())) File "/opt/conda/envs/py310/lib/python3.10/site-packages/mlc_llm/loader/utils.py", line 33, in check_parameter_usage raise ValueError( ValueError: The following extern parameters do not exist in the weight files: lm_head.weight [1mWeight conversion with arguments:[0m [1m--config[0m /models/Qwen2-1.5B-Instruct/config.json [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') [1m--model-type[0m qwen2 [1m--device[0m cuda:0 [1m--source[0m /models/Qwen2-1.5B-Instruct/model.safetensors.index.json [1m--source-format[0m huggingface-safetensor [1m--output[0m /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Qwen2-1.5B-Instruct --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC [2024-06-06 22:37:49] INFO auto_config.py:116: [92mFound[0m model configuration: /ssd2/models/Qwen2-1.5B-Instruct/config.json [2024-06-06 22:37:49] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. [2024-06-06 22:37:49] INFO qwen2_model.py:50: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) [2024-06-06 22:37:49] INFO qwen2_model.py:67: [1mprefill_chunk_size[0m defaults to 2048 [2024-06-06 22:37:49] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 151643 [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 151643 [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: [151645, 151643] [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mrepetition_penalty[0m: 1.1 [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mtemperature[0m: 0.7 [2024-06-06 22:37:49] INFO gen_config.py:143: [generation_config.json] Setting [1mtop_p[0m: 0.8 [2024-06-06 22:37:49] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer.model [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer.json[0m [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/vocab.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/vocab.json[0m [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/merges.txt. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/merges.txt[0m [2024-06-06 22:37:49] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/added_tokens.json [2024-06-06 22:37:49] INFO gen_config.py:155: [92mFound[0m tokenizer config: /ssd2/models/Qwen2-1.5B-Instruct/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/tokenizer_config.json[0m [2024-06-06 22:37:49] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_level', 'prepend_space_in_encode': False, 'strip_space_in_decode': False} [2024-06-06 22:37:49] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 [2024-06-06 22:37:49] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 [2024-06-06 22:37:49] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/mlc-chat-config.json[0m /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Qwen2-1.5B-Instruct --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC [2024-06-06 22:37:50] INFO auto_config.py:116: [92mFound[0m model configuration: /ssd2/models/Qwen2-1.5B-Instruct/config.json [2024-06-06 22:37:52] INFO auto_device.py:79: [92mFound[0m device: cuda:0 [2024-06-06 22:37:52] INFO auto_device.py:79: [92mFound[0m device: cuda:1 [2024-06-06 22:37:53] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 [2024-06-06 22:37:54] INFO auto_device.py:88: [91mNot found[0m device: metal:0 [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 [2024-06-06 22:37:55] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 [2024-06-06 22:37:56] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 [2024-06-06 22:37:56] INFO auto_device.py:35: Using device: [1mcuda:0[0m [2024-06-06 22:37:56] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Qwen2-1.5B-Instruct [2024-06-06 22:37:56] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch [2024-06-06 22:37:56] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json [2024-06-06 22:37:56] INFO auto_weight.py:107: Using source weight configuration: [1m/ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json[0m. Use `--source` to override. [2024-06-06 22:37:56] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. [2024-06-06 22:37:56] INFO auto_config.py:154: [92mFound[0m model type: [1mqwen2[0m. Use `--model-type` to override. [2024-06-06 22:37:56] INFO qwen2_model.py:50: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (32768) [2024-06-06 22:37:56] INFO qwen2_model.py:67: [1mprefill_chunk_size[0m defaults to 2048 [1mWeight conversion with arguments:[0m [1m--config[0m /ssd2/models/Qwen2-1.5B-Instruct/config.json [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') [1m--model-type[0m qwen2 [1m--device[0m cuda:0 [1m--source[0m /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors.index.json [1m--source-format[0m huggingface-safetensor [1m--output[0m /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC 0%| | 0/198 [00:00<?, ?it/s] [2024-06-06 22:37:58] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors 0%| | 0/198 [00:00<?, ?it/s] [2024-06-06 22:38:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (151936, 1536), dtype: float16 0%| | 0/198 [00:02<?, ?it/s] 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (1536,), dtype: float16 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 1%| | 1/198 [00:03<12:17, 3.74s/it] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 1%| | 1/198 [00:03<12:17, 3.74s/it] 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (1536,), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 2%|β | 4/198 [00:04<02:35, 1.25it/s] 5%|β | 10/198 [00:04<00:49, 3.78it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 5%|β | 10/198 [00:04<00:49, 3.78it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 5%|β | 10/198 [00:04<00:49, 3.78it/s] 6%|β | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 6%|β | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 6%|β | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 6%|β | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (1536,), dtype: float16 6%|β | 12/198 [00:04<00:42, 4.36it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 6%|β | 12/198 [00:04<00:42, 4.36it/s] 9%|β | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 9%|β | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 9%|β | 17/198 [00:04<00:24, 7.42it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 9%|β | 17/198 [00:04<00:24, 7.42it/s] 10%|β | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 10%|β | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 10%|β | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (1536,), dtype: float16 10%|β | 20/198 [00:04<00:21, 8.33it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 10%|β | 20/198 [00:05<00:21, 8.33it/s] 12%|ββ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 12%|ββ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 12%|ββ | 24/198 [00:05<00:15, 11.06it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 12%|ββ | 24/198 [00:05<00:15, 11.06it/s] 14%|ββ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 14%|ββ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 14%|ββ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (1536,), dtype: float16 14%|ββ | 27/198 [00:05<00:15, 11.30it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 14%|ββ | 27/198 [00:05<00:15, 11.30it/s] 16%|ββ | 31/198 [00:05<00:12, 13.34it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 16%|ββ | 31/198 [00:05<00:12, 13.34it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 16%|ββ | 31/198 [00:05<00:12, 13.34it/s] 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (1536,), dtype: float16 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 17%|ββ | 33/198 [00:05<00:13, 11.79it/s] 19%|ββ | 38/198 [00:05<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 19%|ββ | 38/198 [00:06<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 19%|ββ | 38/198 [00:06<00:09, 16.36it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 19%|ββ | 38/198 [00:06<00:09, 16.36it/s] 21%|ββ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 21%|ββ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 21%|ββ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (1536,), dtype: float16 21%|ββ | 41/198 [00:06<00:10, 14.94it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 21%|ββ | 41/198 [00:06<00:10, 14.94it/s] 23%|βββ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 23%|βββ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 23%|βββ | 45/198 [00:06<00:08, 17.52it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 23%|βββ | 45/198 [00:06<00:08, 17.52it/s] 24%|βββ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 24%|βββ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 24%|βββ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (1536,), dtype: float16 24%|βββ | 48/198 [00:06<00:09, 15.28it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 24%|βββ | 48/198 [00:06<00:09, 15.28it/s] 26%|βββ | 52/198 [00:06<00:08, 16.47it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 26%|βββ | 52/198 [00:06<00:08, 16.47it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 26%|βββ | 52/198 [00:07<00:08, 16.47it/s] 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (1536,), dtype: float16 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] [2024-06-06 22:38:05] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 27%|βββ | 54/198 [00:07<00:10, 13.51it/s] 30%|βββ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 30%|βββ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 30%|βββ | 59/198 [00:07<00:07, 18.05it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 30%|βββ | 59/198 [00:07<00:07, 18.05it/s] 31%|ββββ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 31%|ββββ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 31%|ββββ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (1536,), dtype: float16 31%|ββββ | 62/198 [00:07<00:08, 15.72it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 31%|ββββ | 62/198 [00:07<00:08, 15.72it/s] 33%|ββββ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 33%|ββββ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 33%|ββββ | 66/198 [00:07<00:07, 18.21it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 33%|ββββ | 66/198 [00:07<00:07, 18.21it/s] 35%|ββββ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 35%|ββββ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 35%|ββββ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (1536,), dtype: float16 35%|ββββ | 69/198 [00:07<00:08, 15.96it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 35%|ββββ | 69/198 [00:07<00:08, 15.96it/s] 37%|ββββ | 73/198 [00:08<00:07, 17.19it/s] [2024-06-06 22:38:06] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 37%|ββββ | 73/198 [00:08<00:07, 17.19it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 37%|ββββ | 73/198 [00:08<00:07, 17.19it/s] 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (1536,), dtype: float16 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 38%|ββββ | 75/198 [00:08<00:08, 14.09it/s] 40%|ββββ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 40%|ββββ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 40%|ββββ | 80/198 [00:08<00:06, 18.76it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 40%|ββββ | 80/198 [00:08<00:06, 18.76it/s] 42%|βββββ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 42%|βββββ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 42%|βββββ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (1536,), dtype: float16 42%|βββββ | 83/198 [00:08<00:07, 16.28it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 42%|βββββ | 83/198 [00:08<00:07, 16.28it/s] 44%|βββββ | 87/198 [00:08<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 44%|βββββ | 87/198 [00:08<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 44%|βββββ | 87/198 [00:09<00:05, 18.73it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 44%|βββββ | 87/198 [00:09<00:05, 18.73it/s] 45%|βββββ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 45%|βββββ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 45%|βββββ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:07] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (1536,), dtype: float16 45%|βββββ | 90/198 [00:09<00:06, 16.24it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 45%|βββββ | 90/198 [00:09<00:06, 16.24it/s] 47%|βββββ | 94/198 [00:09<00:05, 17.41it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 47%|βββββ | 94/198 [00:09<00:05, 17.41it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 47%|βββββ | 94/198 [00:09<00:05, 17.41it/s] 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (1536,), dtype: float16 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 48%|βββββ | 96/198 [00:09<00:07, 14.21it/s] 51%|βββββ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 51%|βββββ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 51%|βββββ | 101/198 [00:09<00:05, 18.90it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 51%|βββββ | 101/198 [00:09<00:05, 18.90it/s] 53%|ββββββ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 53%|ββββββ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 53%|ββββββ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.input_layernorm.weight[0m", shape: (1536,), dtype: float16 53%|ββββββ | 104/198 [00:09<00:05, 16.42it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 53%|ββββββ | 104/198 [00:09<00:05, 16.42it/s] 55%|ββββββ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:08] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 55%|ββββββ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 55%|ββββββ | 108/198 [00:10<00:04, 18.92it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 55%|ββββββ | 108/198 [00:10<00:04, 18.92it/s] 56%|ββββββ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 56%|ββββββ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.22.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 56%|ββββββ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.input_layernorm.weight[0m", shape: (1536,), dtype: float16 56%|ββββββ | 111/198 [00:10<00:05, 16.19it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 56%|ββββββ | 111/198 [00:10<00:05, 16.19it/s] 58%|ββββββ | 115/198 [00:10<00:04, 17.36it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 58%|ββββββ | 115/198 [00:10<00:04, 17.36it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 58%|ββββββ | 115/198 [00:10<00:04, 17.36it/s] 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.23.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.input_layernorm.weight[0m", shape: (1536,), dtype: float16 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 59%|ββββββ | 117/198 [00:10<00:05, 14.20it/s] 62%|βββββββ | 122/198 [00:10<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 62%|βββββββ | 122/198 [00:11<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 62%|βββββββ | 122/198 [00:11<00:04, 18.89it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 62%|βββββββ | 122/198 [00:11<00:04, 18.89it/s] 63%|βββββββ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 63%|βββββββ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.24.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 63%|βββββββ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:09] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.input_layernorm.weight[0m", shape: (1536,), dtype: float16 63%|βββββββ | 125/198 [00:11<00:04, 16.47it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 63%|βββββββ | 125/198 [00:11<00:04, 16.47it/s] 65%|βββββββ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 65%|βββββββ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 65%|βββββββ | 129/198 [00:11<00:03, 19.03it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 65%|βββββββ | 129/198 [00:11<00:03, 19.03it/s] 67%|βββββββ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 67%|βββββββ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.25.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 67%|βββββββ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.input_layernorm.weight[0m", shape: (1536,), dtype: float16 67%|βββββββ | 132/198 [00:11<00:04, 16.50it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 67%|βββββββ | 132/198 [00:11<00:04, 16.50it/s] 69%|βββββββ | 136/198 [00:11<00:03, 17.60it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 69%|βββββββ | 136/198 [00:11<00:03, 17.60it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 69%|βββββββ | 136/198 [00:11<00:03, 17.60it/s] 70%|βββββββ | 138/198 [00:11<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 70%|βββββββ | 138/198 [00:11<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 70%|βββββββ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.26.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 70%|βββββββ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.input_layernorm.weight[0m", shape: (1536,), dtype: float16 70%|βββββββ | 138/198 [00:12<00:04, 14.32it/s] [2024-06-06 22:38:10] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 70%|βββββββ | 138/198 [00:12<00:04, 14.32it/s] 72%|ββββββββ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 72%|ββββββββ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 72%|ββββββββ | 143/198 [00:12<00:02, 19.01it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 72%|ββββββββ | 143/198 [00:12<00:02, 19.01it/s] 74%|ββββββββ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 74%|ββββββββ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.27.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 74%|ββββββββ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (1536,), dtype: float16 74%|ββββββββ | 146/198 [00:12<00:03, 16.53it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 74%|ββββββββ | 146/198 [00:12<00:03, 16.53it/s] 76%|ββββββββ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 76%|ββββββββ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 76%|ββββββββ | 150/198 [00:12<00:02, 19.07it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 76%|ββββββββ | 150/198 [00:12<00:02, 19.07it/s] 77%|ββββββββ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 77%|ββββββββ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 77%|ββββββββ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (1536,), dtype: float16 77%|ββββββββ | 153/198 [00:12<00:02, 16.50it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 77%|ββββββββ | 153/198 [00:12<00:02, 16.50it/s] 79%|ββββββββ | 157/198 [00:12<00:02, 17.62it/s] [2024-06-06 22:38:11] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 79%|ββββββββ | 157/198 [00:13<00:02, 17.62it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 79%|ββββββββ | 157/198 [00:13<00:02, 17.62it/s] 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (1536,), dtype: float16 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 80%|ββββββββ | 159/198 [00:13<00:02, 14.34it/s] 83%|βββββββββ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 83%|βββββββββ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 83%|βββββββββ | 164/198 [00:13<00:01, 19.03it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 83%|βββββββββ | 164/198 [00:13<00:01, 19.03it/s] 84%|βββββββββ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 84%|βββββββββ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 84%|βββββββββ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (1536,), dtype: float16 84%|βββββββββ | 167/198 [00:13<00:01, 16.56it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 84%|βββββββββ | 167/198 [00:13<00:01, 16.56it/s] 86%|βββββββββ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 86%|βββββββββ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 86%|βββββββββ | 171/198 [00:13<00:01, 19.12it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 86%|βββββββββ | 171/198 [00:14<00:01, 19.12it/s] 88%|βββββββββ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 88%|βββββββββ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 88%|βββββββββ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (1536,), dtype: float16 88%|βββββββββ | 174/198 [00:14<00:01, 16.58it/s] [2024-06-06 22:38:12] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 88%|βββββββββ | 174/198 [00:14<00:01, 16.58it/s] 90%|βββββββββ | 178/198 [00:14<00:01, 17.67it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 90%|βββββββββ | 178/198 [00:14<00:01, 17.67it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 90%|βββββββββ | 178/198 [00:14<00:01, 17.67it/s] 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (1536,), dtype: float16 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 91%|βββββββββ | 180/198 [00:14<00:01, 14.28it/s] 93%|ββββββββββ| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 93%|ββββββββββ| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 93%|ββββββββββ| 185/198 [00:14<00:00, 18.87it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 93%|ββββββββββ| 185/198 [00:14<00:00, 18.87it/s] 95%|ββββββββββ| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 95%|ββββββββββ| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 95%|ββββββββββ| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (1536,), dtype: float16 95%|ββββββββββ| 188/198 [00:14<00:00, 16.23it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (1536, 8960), dtype: float16 95%|ββββββββββ| 188/198 [00:14<00:00, 16.23it/s] 97%|ββββββββββ| 192/198 [00:14<00:00, 18.80it/s] [2024-06-06 22:38:13] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (17920, 1536), dtype: float16 97%|ββββββββββ| 192/198 [00:15<00:00, 18.80it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (1536,), dtype: float16 97%|ββββββββββ| 192/198 [00:15<00:00, 18.80it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.bias[0m", shape: (2048,), dtype: float16 97%|ββββββββββ| 192/198 [00:15<00:00, 18.80it/s] 98%|ββββββββββ| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.c_attn.weight[0m", shape: (2048, 1536), dtype: float16 98%|ββββββββββ| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (1536, 1536), dtype: float16 98%|ββββββββββ| 195/198 [00:15<00:00, 16.37it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (1536,), dtype: float16 98%|ββββββββββ| 195/198 [00:15<00:00, 16.37it/s] 100%|ββββββββββ| 198/198 [00:15<00:00, 12.92it/s] [2024-06-06 22:38:14] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Qwen2-1.5B-Instruct/model.safetensors [2024-06-06 22:38:14] INFO stats.py:77: [92mTime usage[0m: HF loading: 1.873 sec; Pre-quantization mapping: 5.689 sec; Quantization: 0.000 sec [2024-06-06 22:38:14] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 5.751 GB. Total bytes loaded from disk: 5.751 GB [2024-06-06 22:38:14] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 2.875 GB [2024-06-06 22:38:14] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,543,714,304 [2024-06-06 22:38:14] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000 [2024-06-06 22:38:14] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC[0m All finished, 67 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Qwen2-1.5B-Instruct-q0f16-MLC/ndarray-cache.json |