File size: 66,893 Bytes
7d2985c |
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 |
/home/msyu/workspace/venv/bin/python -m mlc_llm gen_config /tmp/tmpy7oe9l51/repo --quantization q0f32 --conv-template phi-3 --output /tmp/tmptqlm3cdw
[2024-05-08 13:34:15] INFO auto_config.py:115: [92mFound[0m model configuration: /tmp/tmpy7oe9l51/repo/config.json
[2024-05-08 13:34:15] INFO auto_config.py:153: [92mFound[0m model type: [1mphi3[0m. Use `--model-type` to override.
[2024-05-08 13:34:15] INFO phi3_model.py:53: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-05-08 13:34:15] INFO phi3_model.py:68: [1mprefill_chunk_size[0m defaults to 2048
[2024-05-08 13:34:15] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
[2024-05-08 13:34:15] INFO gen_config.py:255: [generation_config.json] Setting [1mbos_token_id[0m: 1
[2024-05-08 13:34:15] INFO gen_config.py:255: [generation_config.json] Setting [1meos_token_id[0m: [32000, 32001, 32007]
[2024-05-08 13:34:15] INFO gen_config.py:255: [generation_config.json] Setting [1mpad_token_id[0m: 32000
[2024-05-08 13:34:15] INFO gen_config.py:267: [92mFound[0m tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.model. Copying to [1m/tmp/tmptqlm3cdw/tokenizer.model[0m
[2024-05-08 13:34:15] INFO gen_config.py:267: [92mFound[0m tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer.json. Copying to [1m/tmp/tmptqlm3cdw/tokenizer.json[0m
[2024-05-08 13:34:15] INFO gen_config.py:269: [91mNot found[0m tokenizer config: /tmp/tmpy7oe9l51/repo/vocab.json
[2024-05-08 13:34:15] INFO gen_config.py:269: [91mNot found[0m tokenizer config: /tmp/tmpy7oe9l51/repo/merges.txt
[2024-05-08 13:34:15] INFO gen_config.py:267: [92mFound[0m tokenizer config: /tmp/tmpy7oe9l51/repo/added_tokens.json. Copying to [1m/tmp/tmptqlm3cdw/added_tokens.json[0m
[2024-05-08 13:34:15] INFO gen_config.py:267: [92mFound[0m tokenizer config: /tmp/tmpy7oe9l51/repo/tokenizer_config.json. Copying to [1m/tmp/tmptqlm3cdw/tokenizer_config.json[0m
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mtemperature[0m: 0.7
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mpresence_penalty[0m: 0.0
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mfrequency_penalty[0m: 0.0
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mrepetition_penalty[0m: 1.0
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mtop_p[0m: 0.95
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mmean_gen_len[0m: 128
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mmax_gen_len[0m: 512
[2024-05-08 13:34:15] INFO gen_config.py:80: [System default] Setting [1mshift_fill_factor[0m: 0.3
[2024-05-08 13:34:15] INFO gen_config.py:335: Dumping configuration file to: [1m/tmp/tmptqlm3cdw/mlc-chat-config.json[0m
/home/msyu/workspace/venv/bin/python -m mlc_llm convert_weight /tmp/tmpy7oe9l51/repo --quantization q0f32 --source-format auto --output /tmp/tmptqlm3cdw
[2024-05-08 13:34:16] INFO auto_config.py:115: [92mFound[0m model configuration: /tmp/tmpy7oe9l51/repo/config.json
[2024-05-08 13:34:16] INFO auto_device.py:79: [92mFound[0m device: cuda:0
[2024-05-08 13:34:17] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
[2024-05-08 13:34:18] INFO auto_device.py:88: [91mNot found[0m device: metal:0
[2024-05-08 13:34:18] INFO auto_device.py:88: [91mNot found[0m device: vulkan:0
[2024-05-08 13:34:19] INFO auto_device.py:79: [92mFound[0m device: opencl:0
[2024-05-08 13:34:19] INFO auto_device.py:35: Using device: [1mcuda:0[0m
[2024-05-08 13:34:19] INFO auto_weight.py:70: Finding weights in: /tmp/tmpy7oe9l51/repo
[2024-05-08 13:34:19] INFO auto_weight.py:136: [91mNot found[0m Huggingface PyTorch
[2024-05-08 13:34:19] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
[2024-05-08 13:34:19] INFO auto_weight.py:106: Using source weight configuration: [1m/tmp/tmpy7oe9l51/repo/model.safetensors.index.json[0m. Use `--source` to override.
[2024-05-08 13:34:19] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
[2024-05-08 13:34:19] INFO auto_config.py:153: [92mFound[0m model type: [1mphi3[0m. Use `--model-type` to override.
[2024-05-08 13:34:19] INFO phi3_model.py:53: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-05-08 13:34:19] INFO phi3_model.py:68: [1mprefill_chunk_size[0m defaults to 2048
[1mWeight conversion with arguments:[0m
[1m--config[0m /tmp/tmpy7oe9l51/repo/config.json
[1m--quantization[0m NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32')
[1m--model-type[0m phi3
[1m--device[0m cuda:0
[1m--source[0m /tmp/tmpy7oe9l51/repo/model.safetensors.index.json
[1m--source-format[0m huggingface-safetensor
[1m--output[0m /tmp/tmptqlm3cdw
Start storing to cache /tmp/tmptqlm3cdw
0%| | 0/195 [00:00<?, ?it/s]
[2024-05-08 13:34:20] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpy7oe9l51/repo/model-00002-of-00002.safetensors
0%| | 0/195 [00:00<?, ?it/s]
[2024-05-08 13:34:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (32064, 3072), dtype: float32
0%| | 0/195 [00:01<?, ?it/s]/home/msyu/workspace/venv/lib/python3.10/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
setattr(self, word, getattr(machar, word).flat[0])
/home/msyu/workspace/venv/lib/python3.10/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)
1%| | 1/195 [00:02<07:35, 2.35s/it]
[2024-05-08 13:34:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.ln.weight[0m", shape: (3072,), dtype: float32
1%| | 1/195 [00:02<07:35, 2.35s/it]
[2024-05-08 13:34:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
1%| | 1/195 [00:02<07:35, 2.35s/it]
2%|▏ | 3/195 [00:02<02:14, 1.43it/s]
[2024-05-08 13:34:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
2%|▏ | 3/195 [00:02<02:14, 1.43it/s]
2%|▏ | 4/195 [00:03<01:58, 1.61it/s]
[2024-05-08 13:34:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
2%|▏ | 4/195 [00:03<01:58, 1.61it/s]
[2024-05-08 13:34:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
2%|▏ | 4/195 [00:03<01:58, 1.61it/s]
3%|▎ | 6/195 [00:03<01:11, 2.64it/s]
[2024-05-08 13:34:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.ln.weight[0m", shape: (3072,), dtype: float32
3%|▎ | 6/195 [00:03<01:11, 2.64it/s]
[2024-05-08 13:34:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
3%|▎ | 6/195 [00:03<01:11, 2.64it/s]
4%|▍ | 8/195 [00:03<00:50, 3.69it/s]
[2024-05-08 13:34:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
4%|▍ | 8/195 [00:03<00:50, 3.69it/s]
5%|▍ | 9/195 [00:04<00:58, 3.16it/s]
[2024-05-08 13:34:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
5%|▍ | 9/195 [00:04<00:58, 3.16it/s]
[2024-05-08 13:34:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
5%|▍ | 9/195 [00:04<00:58, 3.16it/s]
[2024-05-08 13:34:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.22.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
5%|▍ | 9/195 [00:04<00:58, 3.16it/s]
6%|▌ | 12/195 [00:04<00:39, 4.64it/s]
[2024-05-08 13:34:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.ln.weight[0m", shape: (3072,), dtype: float32
6%|▌ | 12/195 [00:04<00:39, 4.64it/s]
[2024-05-08 13:34:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
6%|▌ | 12/195 [00:04<00:39, 4.64it/s]
7%|▋ | 14/195 [00:04<00:33, 5.41it/s]
[2024-05-08 13:34:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
7%|▋ | 14/195 [00:04<00:33, 5.41it/s]
8%|▊ | 15/195 [00:05<00:42, 4.21it/s]
[2024-05-08 13:34:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
8%|▊ | 15/195 [00:05<00:42, 4.21it/s]
[2024-05-08 13:34:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
8%|▊ | 15/195 [00:05<00:42, 4.21it/s]
[2024-05-08 13:34:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.23.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
8%|▊ | 15/195 [00:05<00:42, 4.21it/s]
9%|▉ | 18/195 [00:05<00:32, 5.42it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.ln.weight[0m", shape: (3072,), dtype: float32
9%|▉ | 18/195 [00:05<00:32, 5.42it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
9%|▉ | 18/195 [00:05<00:32, 5.42it/s]
10%|█ | 20/195 [00:05<00:28, 6.06it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
10%|█ | 20/195 [00:05<00:28, 6.06it/s]
11%|█ | 21/195 [00:06<00:37, 4.59it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
11%|█ | 21/195 [00:06<00:37, 4.59it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
11%|█ | 21/195 [00:06<00:37, 4.59it/s]
[2024-05-08 13:34:26] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.24.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
11%|█ | 21/195 [00:06<00:37, 4.59it/s]
12%|█▏ | 24/195 [00:06<00:29, 5.72it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.ln.weight[0m", shape: (3072,), dtype: float32
12%|█▏ | 24/195 [00:06<00:29, 5.72it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
12%|█▏ | 24/195 [00:06<00:29, 5.72it/s]
13%|█▎ | 26/195 [00:06<00:26, 6.30it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
13%|█▎ | 26/195 [00:06<00:26, 6.30it/s]
14%|█▍ | 27/195 [00:07<00:37, 4.54it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
14%|█▍ | 27/195 [00:07<00:37, 4.54it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
14%|█▍ | 27/195 [00:07<00:37, 4.54it/s]
[2024-05-08 13:34:27] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.25.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
14%|█▍ | 27/195 [00:07<00:37, 4.54it/s]
15%|█▌ | 30/195 [00:07<00:29, 5.66it/s]
[2024-05-08 13:34:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.ln.weight[0m", shape: (3072,), dtype: float32
15%|█▌ | 30/195 [00:07<00:29, 5.66it/s]
[2024-05-08 13:34:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
15%|█▌ | 30/195 [00:07<00:29, 5.66it/s]
16%|█▋ | 32/195 [00:07<00:26, 6.24it/s]
[2024-05-08 13:34:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
16%|█▋ | 32/195 [00:07<00:26, 6.24it/s]
17%|█▋ | 33/195 [00:08<00:36, 4.46it/s]
[2024-05-08 13:34:28] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
17%|█▋ | 33/195 [00:08<00:36, 4.46it/s]
[2024-05-08 13:34:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
17%|█▋ | 33/195 [00:08<00:36, 4.46it/s]
[2024-05-08 13:34:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.26.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
17%|█▋ | 33/195 [00:08<00:36, 4.46it/s]
18%|█▊ | 36/195 [00:08<00:28, 5.59it/s]
[2024-05-08 13:34:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.ln.weight[0m", shape: (3072,), dtype: float32
18%|█▊ | 36/195 [00:08<00:28, 5.59it/s]
[2024-05-08 13:34:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
18%|█▊ | 36/195 [00:08<00:28, 5.59it/s]
19%|█▉ | 38/195 [00:09<00:30, 5.13it/s]
[2024-05-08 13:34:29] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
19%|█▉ | 38/195 [00:09<00:30, 5.13it/s]
20%|██ | 39/195 [00:09<00:39, 3.90it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
20%|██ | 39/195 [00:09<00:39, 3.90it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
20%|██ | 39/195 [00:09<00:39, 3.90it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.27.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
20%|██ | 39/195 [00:09<00:39, 3.90it/s]
22%|██▏ | 42/195 [00:10<00:30, 5.06it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.ln.weight[0m", shape: (3072,), dtype: float32
22%|██▏ | 42/195 [00:10<00:30, 5.06it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
22%|██▏ | 42/195 [00:10<00:30, 5.06it/s]
23%|██▎ | 44/195 [00:10<00:26, 5.71it/s]
[2024-05-08 13:34:30] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
23%|██▎ | 44/195 [00:10<00:26, 5.71it/s]
23%|██▎ | 45/195 [00:10<00:35, 4.21it/s]
[2024-05-08 13:34:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
23%|██▎ | 45/195 [00:10<00:35, 4.21it/s]
[2024-05-08 13:34:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
23%|██▎ | 45/195 [00:10<00:35, 4.21it/s]
[2024-05-08 13:34:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.28.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
23%|██▎ | 45/195 [00:10<00:35, 4.21it/s]
25%|██▍ | 48/195 [00:11<00:27, 5.34it/s]
[2024-05-08 13:34:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.ln.weight[0m", shape: (3072,), dtype: float32
25%|██▍ | 48/195 [00:11<00:27, 5.34it/s]
[2024-05-08 13:34:31] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
25%|██▍ | 48/195 [00:11<00:27, 5.34it/s]
26%|██▌ | 50/195 [00:11<00:24, 5.96it/s]
[2024-05-08 13:34:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
26%|██▌ | 50/195 [00:11<00:24, 5.96it/s]
26%|██▌ | 51/195 [00:12<00:33, 4.29it/s]
[2024-05-08 13:34:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
26%|██▌ | 51/195 [00:12<00:33, 4.29it/s]
[2024-05-08 13:34:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
26%|██▌ | 51/195 [00:12<00:33, 4.29it/s]
[2024-05-08 13:34:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.29.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
26%|██▌ | 51/195 [00:12<00:33, 4.29it/s]
28%|██▊ | 54/195 [00:12<00:25, 5.43it/s]
[2024-05-08 13:34:32] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.ln.weight[0m", shape: (3072,), dtype: float32
28%|██▊ | 54/195 [00:12<00:25, 5.43it/s]
[2024-05-08 13:34:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
28%|██▊ | 54/195 [00:12<00:25, 5.43it/s]
29%|██▊ | 56/195 [00:12<00:23, 6.03it/s]
[2024-05-08 13:34:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
29%|██▊ | 56/195 [00:12<00:23, 6.03it/s]
29%|██▉ | 57/195 [00:13<00:32, 4.28it/s]
[2024-05-08 13:34:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
29%|██▉ | 57/195 [00:13<00:32, 4.28it/s]
[2024-05-08 13:34:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
29%|██▉ | 57/195 [00:13<00:32, 4.28it/s]
[2024-05-08 13:34:33] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.30.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
29%|██▉ | 57/195 [00:13<00:32, 4.28it/s]
31%|███ | 60/195 [00:13<00:24, 5.42it/s]
[2024-05-08 13:34:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.ln.weight[0m", shape: (3072,), dtype: float32
31%|███ | 60/195 [00:13<00:24, 5.42it/s]
[2024-05-08 13:34:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
31%|███ | 60/195 [00:13<00:24, 5.42it/s]
32%|███▏ | 62/195 [00:13<00:22, 6.02it/s]
[2024-05-08 13:34:34] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
32%|███▏ | 62/195 [00:13<00:22, 6.02it/s]
32%|███▏ | 63/195 [00:14<00:44, 2.96it/s]
[2024-05-08 13:34:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
32%|███▏ | 63/195 [00:14<00:44, 2.96it/s]
[2024-05-08 13:34:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
32%|███▏ | 63/195 [00:14<00:44, 2.96it/s]
[2024-05-08 13:34:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.31.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
32%|███▏ | 63/195 [00:15<00:44, 2.96it/s]
34%|███▍ | 66/195 [00:15<00:31, 4.05it/s]
[2024-05-08 13:34:35] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.norm.weight[0m", shape: (3072,), dtype: float32
34%|███▍ | 66/195 [00:15<00:31, 4.05it/s]
[2024-05-08 13:34:35] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpy7oe9l51/repo/model-00002-of-00002.safetensors
34%|███▍ | 66/195 [00:15<00:31, 4.05it/s]
[2024-05-08 13:34:36] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpy7oe9l51/repo/model-00001-of-00002.safetensors
34%|███▍ | 66/195 [00:15<00:31, 4.05it/s]
[2024-05-08 13:34:36] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.embd.weight[0m", shape: (32064, 3072), dtype: float32
34%|███▍ | 66/195 [00:16<00:31, 4.05it/s]
35%|███▍ | 68/195 [00:17<01:01, 2.08it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.ln.weight[0m", shape: (3072,), dtype: float32
35%|███▍ | 68/195 [00:17<01:01, 2.08it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
35%|███▍ | 68/195 [00:17<01:01, 2.08it/s]
36%|███▌ | 70/195 [00:17<00:47, 2.65it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
36%|███▌ | 70/195 [00:17<00:47, 2.65it/s]
36%|███▋ | 71/195 [00:18<00:48, 2.55it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
36%|███▋ | 71/195 [00:18<00:48, 2.55it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
36%|███▋ | 71/195 [00:18<00:48, 2.55it/s]
[2024-05-08 13:34:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.0.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
36%|███▋ | 71/195 [00:18<00:48, 2.55it/s]
38%|███▊ | 74/195 [00:18<00:33, 3.61it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.ln.weight[0m", shape: (3072,), dtype: float32
38%|███▊ | 74/195 [00:18<00:33, 3.61it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
38%|███▊ | 74/195 [00:18<00:33, 3.61it/s]
39%|███▉ | 76/195 [00:18<00:27, 4.32it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
39%|███▉ | 76/195 [00:18<00:27, 4.32it/s]
39%|███▉ | 77/195 [00:19<00:32, 3.67it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
39%|███▉ | 77/195 [00:19<00:32, 3.67it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
39%|███▉ | 77/195 [00:19<00:32, 3.67it/s]
[2024-05-08 13:34:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.1.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
39%|███▉ | 77/195 [00:19<00:32, 3.67it/s]
41%|████ | 80/195 [00:19<00:23, 4.82it/s]
[2024-05-08 13:34:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.ln.weight[0m", shape: (3072,), dtype: float32
41%|████ | 80/195 [00:19<00:23, 4.82it/s]
[2024-05-08 13:34:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
41%|████ | 80/195 [00:19<00:23, 4.82it/s]
42%|████▏ | 82/195 [00:19<00:20, 5.49it/s]
[2024-05-08 13:34:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
42%|████▏ | 82/195 [00:19<00:20, 5.49it/s]
43%|████▎ | 83/195 [00:20<00:25, 4.33it/s]
[2024-05-08 13:34:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
43%|████▎ | 83/195 [00:20<00:25, 4.33it/s]
[2024-05-08 13:34:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
43%|████▎ | 83/195 [00:20<00:25, 4.33it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.10.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
43%|████▎ | 83/195 [00:20<00:25, 4.33it/s]
44%|████▍ | 86/195 [00:20<00:20, 5.45it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.ln.weight[0m", shape: (3072,), dtype: float32
44%|████▍ | 86/195 [00:20<00:20, 5.45it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
44%|████▍ | 86/195 [00:20<00:20, 5.45it/s]
45%|████▌ | 88/195 [00:20<00:17, 6.06it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
45%|████▌ | 88/195 [00:20<00:17, 6.06it/s]
46%|████▌ | 89/195 [00:21<00:22, 4.62it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
46%|████▌ | 89/195 [00:21<00:22, 4.62it/s]
[2024-05-08 13:34:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
46%|████▌ | 89/195 [00:21<00:22, 4.62it/s]
[2024-05-08 13:34:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.11.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
46%|████▌ | 89/195 [00:21<00:22, 4.62it/s]
47%|████▋ | 92/195 [00:21<00:18, 5.71it/s]
[2024-05-08 13:34:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.ln.weight[0m", shape: (3072,), dtype: float32
47%|████▋ | 92/195 [00:21<00:18, 5.71it/s]
[2024-05-08 13:34:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
47%|████▋ | 92/195 [00:21<00:18, 5.71it/s]
48%|████▊ | 94/195 [00:21<00:16, 6.29it/s]
[2024-05-08 13:34:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
48%|████▊ | 94/195 [00:21<00:16, 6.29it/s]
49%|████▊ | 95/195 [00:22<00:21, 4.69it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
49%|████▊ | 95/195 [00:22<00:21, 4.69it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
49%|████▊ | 95/195 [00:22<00:21, 4.69it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.12.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
49%|████▊ | 95/195 [00:22<00:21, 4.69it/s]
50%|█████ | 98/195 [00:22<00:16, 5.77it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.ln.weight[0m", shape: (3072,), dtype: float32
50%|█████ | 98/195 [00:22<00:16, 5.77it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
50%|█████ | 98/195 [00:22<00:16, 5.77it/s]
51%|█████▏ | 100/195 [00:23<00:14, 6.34it/s]
[2024-05-08 13:34:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
51%|█████▏ | 100/195 [00:23<00:14, 6.34it/s]
52%|█████▏ | 101/195 [00:23<00:20, 4.67it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
52%|█████▏ | 101/195 [00:23<00:20, 4.67it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
52%|█████▏ | 101/195 [00:23<00:20, 4.67it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.13.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
52%|█████▏ | 101/195 [00:23<00:20, 4.67it/s]
53%|█████▎ | 104/195 [00:23<00:15, 5.75it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.ln.weight[0m", shape: (3072,), dtype: float32
53%|█████▎ | 104/195 [00:23<00:15, 5.75it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
53%|█████▎ | 104/195 [00:23<00:15, 5.75it/s]
54%|█████▍ | 106/195 [00:24<00:14, 6.33it/s]
[2024-05-08 13:34:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
54%|█████▍ | 106/195 [00:24<00:14, 6.33it/s]
55%|█████▍ | 107/195 [00:24<00:18, 4.69it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
55%|█████▍ | 107/195 [00:24<00:18, 4.69it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
55%|█████▍ | 107/195 [00:24<00:18, 4.69it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.14.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
55%|█████▍ | 107/195 [00:24<00:18, 4.69it/s]
56%|█████▋ | 110/195 [00:24<00:14, 5.77it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.ln.weight[0m", shape: (3072,), dtype: float32
56%|█████▋ | 110/195 [00:24<00:14, 5.77it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
56%|█████▋ | 110/195 [00:24<00:14, 5.77it/s]
57%|█████▋ | 112/195 [00:25<00:13, 6.34it/s]
[2024-05-08 13:34:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
57%|█████▋ | 112/195 [00:25<00:13, 6.34it/s]
58%|█████▊ | 113/195 [00:25<00:17, 4.65it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
58%|█████▊ | 113/195 [00:25<00:17, 4.65it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
58%|█████▊ | 113/195 [00:25<00:17, 4.65it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.15.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
58%|█████▊ | 113/195 [00:25<00:17, 4.65it/s]
59%|█████▉ | 116/195 [00:26<00:13, 5.70it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.ln.weight[0m", shape: (3072,), dtype: float32
59%|█████▉ | 116/195 [00:26<00:13, 5.70it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
59%|█████▉ | 116/195 [00:26<00:13, 5.70it/s]
61%|██████ | 118/195 [00:26<00:12, 6.22it/s]
[2024-05-08 13:34:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
61%|██████ | 118/195 [00:26<00:12, 6.22it/s]
61%|██████ | 119/195 [00:26<00:17, 4.47it/s]
[2024-05-08 13:34:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
61%|██████ | 119/195 [00:26<00:17, 4.47it/s]
[2024-05-08 13:34:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
61%|██████ | 119/195 [00:26<00:17, 4.47it/s]
[2024-05-08 13:34:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.16.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
61%|██████ | 119/195 [00:26<00:17, 4.47it/s]
63%|██████▎ | 122/195 [00:27<00:13, 5.57it/s]
[2024-05-08 13:34:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.ln.weight[0m", shape: (3072,), dtype: float32
63%|██████▎ | 122/195 [00:27<00:13, 5.57it/s]
[2024-05-08 13:34:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
63%|██████▎ | 122/195 [00:27<00:13, 5.57it/s]
64%|██████▎ | 124/195 [00:27<00:11, 6.17it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
64%|██████▎ | 124/195 [00:27<00:11, 6.17it/s]
64%|██████▍ | 125/195 [00:27<00:15, 4.56it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
64%|██████▍ | 125/195 [00:27<00:15, 4.56it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
64%|██████▍ | 125/195 [00:27<00:15, 4.56it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.17.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
64%|██████▍ | 125/195 [00:28<00:15, 4.56it/s]
66%|██████▌ | 128/195 [00:28<00:11, 5.65it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.ln.weight[0m", shape: (3072,), dtype: float32
66%|██████▌ | 128/195 [00:28<00:11, 5.65it/s]
[2024-05-08 13:34:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
66%|██████▌ | 128/195 [00:28<00:11, 5.65it/s]
67%|██████▋ | 130/195 [00:28<00:10, 6.24it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
67%|██████▋ | 130/195 [00:28<00:10, 6.24it/s]
67%|██████▋ | 131/195 [00:29<00:13, 4.60it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
67%|██████▋ | 131/195 [00:29<00:13, 4.60it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
67%|██████▋ | 131/195 [00:29<00:13, 4.60it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.18.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
67%|██████▋ | 131/195 [00:29<00:13, 4.60it/s]
69%|██████▊ | 134/195 [00:29<00:10, 5.69it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.ln.weight[0m", shape: (3072,), dtype: float32
69%|██████▊ | 134/195 [00:29<00:10, 5.69it/s]
[2024-05-08 13:34:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
69%|██████▊ | 134/195 [00:29<00:10, 5.69it/s]
70%|██████▉ | 136/195 [00:29<00:09, 6.28it/s]
[2024-05-08 13:34:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
70%|██████▉ | 136/195 [00:29<00:09, 6.28it/s]
70%|███████ | 137/195 [00:30<00:13, 4.27it/s]
[2024-05-08 13:34:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
70%|███████ | 137/195 [00:30<00:13, 4.27it/s]
[2024-05-08 13:34:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
70%|███████ | 137/195 [00:30<00:13, 4.27it/s]
[2024-05-08 13:34:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.19.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
70%|███████ | 137/195 [00:30<00:13, 4.27it/s]
72%|███████▏ | 140/195 [00:30<00:10, 5.33it/s]
[2024-05-08 13:34:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.ln.weight[0m", shape: (3072,), dtype: float32
72%|███████▏ | 140/195 [00:30<00:10, 5.33it/s]
[2024-05-08 13:34:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
72%|███████▏ | 140/195 [00:30<00:10, 5.33it/s]
73%|███████▎ | 142/195 [00:30<00:08, 5.93it/s]
[2024-05-08 13:34:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
73%|███████▎ | 142/195 [00:30<00:08, 5.93it/s]
73%|███████▎ | 143/195 [00:31<00:11, 4.50it/s]
[2024-05-08 13:34:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
73%|███████▎ | 143/195 [00:31<00:11, 4.50it/s]
[2024-05-08 13:34:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
73%|███████▎ | 143/195 [00:31<00:11, 4.50it/s]
[2024-05-08 13:34:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.2.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
73%|███████▎ | 143/195 [00:31<00:11, 4.50it/s]
75%|███████▍ | 146/195 [00:31<00:08, 5.60it/s]
[2024-05-08 13:34:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.ln.weight[0m", shape: (3072,), dtype: float32
75%|███████▍ | 146/195 [00:31<00:08, 5.60it/s]
[2024-05-08 13:34:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
75%|███████▍ | 146/195 [00:31<00:08, 5.60it/s]
76%|███████▌ | 148/195 [00:31<00:07, 6.20it/s]
[2024-05-08 13:34:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
76%|███████▌ | 148/195 [00:31<00:07, 6.20it/s]
76%|███████▋ | 149/195 [00:32<00:10, 4.39it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
76%|███████▋ | 149/195 [00:32<00:10, 4.39it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
76%|███████▋ | 149/195 [00:32<00:10, 4.39it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.20.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
76%|███████▋ | 149/195 [00:32<00:10, 4.39it/s]
78%|███████▊ | 152/195 [00:32<00:07, 5.50it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.21.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
78%|███████▊ | 152/195 [00:32<00:07, 5.50it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.ln.weight[0m", shape: (3072,), dtype: float32
78%|███████▊ | 152/195 [00:32<00:07, 5.50it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
78%|███████▊ | 152/195 [00:32<00:07, 5.50it/s]
79%|███████▉ | 155/195 [00:33<00:06, 6.52it/s]
[2024-05-08 13:34:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
79%|███████▉ | 155/195 [00:33<00:06, 6.52it/s]
80%|████████ | 156/195 [00:33<00:08, 4.86it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
80%|████████ | 156/195 [00:33<00:08, 4.86it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
80%|████████ | 156/195 [00:33<00:08, 4.86it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.3.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
80%|████████ | 156/195 [00:33<00:08, 4.86it/s]
82%|████████▏ | 159/195 [00:33<00:06, 5.83it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.ln.weight[0m", shape: (3072,), dtype: float32
82%|████████▏ | 159/195 [00:33<00:06, 5.83it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
82%|████████▏ | 159/195 [00:33<00:06, 5.83it/s]
83%|████████▎ | 161/195 [00:34<00:05, 6.30it/s]
[2024-05-08 13:34:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
83%|████████▎ | 161/195 [00:34<00:05, 6.30it/s]
83%|████████▎ | 162/195 [00:34<00:08, 4.00it/s]
[2024-05-08 13:34:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
83%|████████▎ | 162/195 [00:34<00:08, 4.00it/s]
[2024-05-08 13:34:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
83%|████████▎ | 162/195 [00:34<00:08, 4.00it/s]
[2024-05-08 13:34:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.4.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
83%|████████▎ | 162/195 [00:35<00:08, 4.00it/s]
85%|████████▍ | 165/195 [00:35<00:05, 5.09it/s]
[2024-05-08 13:34:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.ln.weight[0m", shape: (3072,), dtype: float32
85%|████████▍ | 165/195 [00:35<00:05, 5.09it/s]
[2024-05-08 13:34:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
85%|████████▍ | 165/195 [00:35<00:05, 5.09it/s]
86%|████████▌ | 167/195 [00:35<00:04, 5.72it/s]
[2024-05-08 13:34:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
86%|████████▌ | 167/195 [00:35<00:04, 5.72it/s]
86%|████████▌ | 168/195 [00:36<00:06, 4.25it/s]
[2024-05-08 13:34:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
86%|████████▌ | 168/195 [00:36<00:06, 4.25it/s]
[2024-05-08 13:34:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
86%|████████▌ | 168/195 [00:36<00:06, 4.25it/s]
[2024-05-08 13:34:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.5.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
86%|████████▌ | 168/195 [00:36<00:06, 4.25it/s]
88%|████████▊ | 171/195 [00:36<00:04, 5.34it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.ln.weight[0m", shape: (3072,), dtype: float32
88%|████████▊ | 171/195 [00:36<00:04, 5.34it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
88%|████████▊ | 171/195 [00:36<00:04, 5.34it/s]
89%|████████▊ | 173/195 [00:36<00:03, 5.95it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
89%|████████▊ | 173/195 [00:36<00:03, 5.95it/s]
89%|████████▉ | 174/195 [00:37<00:04, 4.39it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
89%|████████▉ | 174/195 [00:37<00:04, 4.39it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
89%|████████▉ | 174/195 [00:37<00:04, 4.39it/s]
[2024-05-08 13:34:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.6.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
89%|████████▉ | 174/195 [00:37<00:04, 4.39it/s]
91%|█████████ | 177/195 [00:37<00:03, 5.50it/s]
[2024-05-08 13:34:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.ln.weight[0m", shape: (3072,), dtype: float32
91%|█████████ | 177/195 [00:37<00:03, 5.50it/s]
[2024-05-08 13:34:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
91%|█████████ | 177/195 [00:37<00:03, 5.50it/s]
92%|█████████▏| 179/195 [00:37<00:02, 6.11it/s]
[2024-05-08 13:34:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
92%|█████████▏| 179/195 [00:37<00:02, 6.11it/s]
92%|█████████▏| 180/195 [00:38<00:03, 4.52it/s]
[2024-05-08 13:34:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
92%|█████████▏| 180/195 [00:38<00:03, 4.52it/s]
[2024-05-08 13:34:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
92%|█████████▏| 180/195 [00:38<00:03, 4.52it/s]
[2024-05-08 13:34:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.7.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
92%|█████████▏| 180/195 [00:38<00:03, 4.52it/s]
94%|█████████▍| 183/195 [00:38<00:02, 5.62it/s]
[2024-05-08 13:34:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.ln.weight[0m", shape: (3072,), dtype: float32
94%|█████████▍| 183/195 [00:38<00:02, 5.62it/s]
[2024-05-08 13:34:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
94%|█████████▍| 183/195 [00:38<00:02, 5.62it/s]
95%|█████████▍| 185/195 [00:38<00:01, 6.21it/s]
[2024-05-08 13:34:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
95%|█████████▍| 185/195 [00:38<00:01, 6.21it/s]
95%|█████████▌| 186/195 [00:39<00:02, 4.07it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
95%|█████████▌| 186/195 [00:39<00:02, 4.07it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
95%|█████████▌| 186/195 [00:39<00:02, 4.07it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.8.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
95%|█████████▌| 186/195 [00:39<00:02, 4.07it/s]
97%|█████████▋| 189/195 [00:39<00:01, 5.21it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.ln.weight[0m", shape: (3072,), dtype: float32
97%|█████████▋| 189/195 [00:39<00:01, 5.21it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.mlp.down_proj.weight[0m", shape: (3072, 8192), dtype: float32
97%|█████████▋| 189/195 [00:39<00:01, 5.21it/s]
98%|█████████▊| 191/195 [00:40<00:00, 5.85it/s]
[2024-05-08 13:35:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.mlp.gate_up_proj.weight[0m", shape: (16384, 3072), dtype: float32
98%|█████████▊| 191/195 [00:40<00:00, 5.85it/s]
98%|█████████▊| 192/195 [00:40<00:00, 4.37it/s]
[2024-05-08 13:35:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.post_attention_layernorm.weight[0m", shape: (3072,), dtype: float32
98%|█████████▊| 192/195 [00:40<00:00, 4.37it/s]
[2024-05-08 13:35:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.mixer.out_proj.weight[0m", shape: (3072, 3072), dtype: float32
98%|█████████▊| 192/195 [00:40<00:00, 4.37it/s]
[2024-05-08 13:35:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "[1mtransformer.h.9.mixer.qkv_proj.weight[0m", shape: (9216, 3072), dtype: float32
98%|█████████▊| 192/195 [00:40<00:00, 4.37it/s]
100%|██████████| 195/195 [00:40<00:00, 5.49it/s]
100%|██████████| 195/195 [00:41<00:00, 4.76it/s]
[2024-05-08 13:35:01] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpy7oe9l51/repo/model-00001-of-00002.safetensors
[2024-05-08 13:35:01] INFO stats.py:76: [92mTime usage[0m: HF loading: 1.642 sec; Pre-quantization mapping: 2.009 sec; Quantization: 0.000 sec
[2024-05-08 13:35:01] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
[2024-05-08 13:35:01] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 14.235 GB
[2024-05-08 13:35:01] INFO convert_weight.py:160: [92mTotal parameters[0m: 3,821,079,552
[2024-05-08 13:35:01] INFO convert_weight.py:161: [92mBits per parameter[0m: 32.000
[2024-05-08 13:35:01] INFO convert_weight.py:166: Saved to directory: [1m/tmp/tmptqlm3cdw[0m
All finished, 130 total shards committed, record saved to /tmp/tmptqlm3cdw/ndarray-cache.json
Also saved a bf16 record to /tmp/tmptqlm3cdw/ndarray-cache-b16.json
|