mengshyu's picture
Initial commit
9bebc2c verified
raw
history blame
66.9 kB
/home/msyu/workspace/venv/bin/python -m mlc_llm gen_config /tmp/tmpom_oz7t5/repo --quantization q0f32 --conv-template phi-3 --output /tmp/tmpbu0nfi81
[2024-05-08 13:43:32] INFO auto_config.py:115: Found model configuration: /tmp/tmpom_oz7t5/repo/config.json
[2024-05-08 13:43:32] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-08 13:43:32] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072)
[2024-05-08 13:43:32] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
[2024-05-08 13:43:32] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-05-08 13:43:32] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
[2024-05-08 13:43:32] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007]
[2024-05-08 13:43:32] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 32000
[2024-05-08 13:43:32] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer.model. Copying to /tmp/tmpbu0nfi81/tokenizer.model
[2024-05-08 13:43:32] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer.json. Copying to /tmp/tmpbu0nfi81/tokenizer.json
[2024-05-08 13:43:32] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpom_oz7t5/repo/vocab.json
[2024-05-08 13:43:32] INFO gen_config.py:269: Not found tokenizer config: /tmp/tmpom_oz7t5/repo/merges.txt
[2024-05-08 13:43:32] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/added_tokens.json. Copying to /tmp/tmpbu0nfi81/added_tokens.json
[2024-05-08 13:43:32] INFO gen_config.py:267: Found tokenizer config: /tmp/tmpom_oz7t5/repo/tokenizer_config.json. Copying to /tmp/tmpbu0nfi81/tokenizer_config.json
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting temperature: 0.7
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting top_p: 0.95
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
[2024-05-08 13:43:32] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
[2024-05-08 13:43:32] INFO gen_config.py:335: Dumping configuration file to: /tmp/tmpbu0nfi81/mlc-chat-config.json
/home/msyu/workspace/venv/bin/python -m mlc_llm convert_weight /tmp/tmpom_oz7t5/repo --quantization q0f32 --source-format auto --output /tmp/tmpbu0nfi81
[2024-05-08 13:43:33] INFO auto_config.py:115: Found model configuration: /tmp/tmpom_oz7t5/repo/config.json
[2024-05-08 13:43:33] INFO auto_device.py:79: Found device: cuda:0
[2024-05-08 13:43:34] INFO auto_device.py:88: Not found device: rocm:0
[2024-05-08 13:43:34] INFO auto_device.py:88: Not found device: metal:0
[2024-05-08 13:43:35] INFO auto_device.py:88: Not found device: vulkan:0
[2024-05-08 13:43:36] INFO auto_device.py:79: Found device: opencl:0
[2024-05-08 13:43:36] INFO auto_device.py:35: Using device: cuda:0
[2024-05-08 13:43:36] INFO auto_weight.py:70: Finding weights in: /tmp/tmpom_oz7t5/repo
[2024-05-08 13:43:36] INFO auto_weight.py:136: Not found Huggingface PyTorch
[2024-05-08 13:43:36] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /tmp/tmpom_oz7t5/repo/model.safetensors.index.json
[2024-05-08 13:43:36] INFO auto_weight.py:106: Using source weight configuration: /tmp/tmpom_oz7t5/repo/model.safetensors.index.json. Use `--source` to override.
[2024-05-08 13:43:36] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-05-08 13:43:36] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-08 13:43:36] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072)
[2024-05-08 13:43:36] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /tmp/tmpom_oz7t5/repo/config.json
--quantization NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32')
--model-type phi3
--device cuda:0
--source /tmp/tmpom_oz7t5/repo/model.safetensors.index.json
--source-format huggingface-safetensor
--output /tmp/tmpbu0nfi81
Start storing to cache /tmp/tmpbu0nfi81
0%| | 0/195 [00:00<?, ?it/s] [2024-05-08 13:43:37] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpom_oz7t5/repo/model-00002-of-00002.safetensors
0%| | 0/195 [00:00<?, ?it/s] [2024-05-08 13:43:38] INFO huggingface_loader.py:174: [Not quantized] Parameter: "lm_head.weight", shape: (32064, 3072), dtype: float32
0%| | 0/195 [00:00<?, ?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 [00:01<05:23, 1.67s/it] [2024-05-08 13:43:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32
1%| | 1/195 [00:01<05:23, 1.67s/it] [2024-05-08 13:43:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
1%| | 1/195 [00:01<05:23, 1.67s/it] 2%|▏ | 3/195 [00:01<01:40, 1.91it/s] [2024-05-08 13:43:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
2%|▏ | 3/195 [00:01<01:40, 1.91it/s] 2%|▏ | 4/195 [00:02<01:36, 1.99it/s] [2024-05-08 13:43:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32
2%|▏ | 4/195 [00:02<01:36, 1.99it/s] [2024-05-08 13:43:39] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
2%|▏ | 4/195 [00:02<01:36, 1.99it/s] 3%|β–Ž | 6/195 [00:02<01:00, 3.13it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32
3%|β–Ž | 6/195 [00:02<01:00, 3.13it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
3%|β–Ž | 6/195 [00:02<01:00, 3.13it/s] 4%|▍ | 8/195 [00:02<00:44, 4.23it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
4%|▍ | 8/195 [00:02<00:44, 4.23it/s] 5%|▍ | 9/195 [00:03<00:53, 3.46it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32
5%|▍ | 9/195 [00:03<00:53, 3.46it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
5%|▍ | 9/195 [00:03<00:53, 3.46it/s] [2024-05-08 13:43:40] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
5%|▍ | 9/195 [00:03<00:53, 3.46it/s] 6%|β–Œ | 12/195 [00:03<00:36, 4.96it/s] [2024-05-08 13:43:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32
6%|β–Œ | 12/195 [00:03<00:36, 4.96it/s] [2024-05-08 13:43:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
6%|β–Œ | 12/195 [00:03<00:36, 4.96it/s] 7%|β–‹ | 14/195 [00:03<00:31, 5.70it/s] [2024-05-08 13:43:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
7%|β–‹ | 14/195 [00:03<00:31, 5.70it/s] 8%|β–Š | 15/195 [00:04<00:41, 4.35it/s] [2024-05-08 13:43:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32
8%|β–Š | 15/195 [00:04<00:41, 4.35it/s] [2024-05-08 13:43:41] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
8%|β–Š | 15/195 [00:04<00:41, 4.35it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
8%|β–Š | 15/195 [00:04<00:41, 4.35it/s] 9%|β–‰ | 18/195 [00:04<00:31, 5.56it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32
9%|β–‰ | 18/195 [00:04<00:31, 5.56it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
9%|β–‰ | 18/195 [00:04<00:31, 5.56it/s] 10%|β–ˆ | 20/195 [00:04<00:28, 6.18it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
10%|β–ˆ | 20/195 [00:05<00:28, 6.18it/s] 11%|β–ˆ | 21/195 [00:05<00:37, 4.64it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32
11%|β–ˆ | 21/195 [00:05<00:37, 4.64it/s] [2024-05-08 13:43:42] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
11%|β–ˆ | 21/195 [00:05<00:37, 4.64it/s] [2024-05-08 13:43:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
11%|β–ˆ | 21/195 [00:05<00:37, 4.64it/s] 12%|β–ˆβ– | 24/195 [00:05<00:29, 5.77it/s] [2024-05-08 13:43:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32
12%|β–ˆβ– | 24/195 [00:05<00:29, 5.77it/s] [2024-05-08 13:43:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
12%|β–ˆβ– | 24/195 [00:05<00:29, 5.77it/s] 13%|β–ˆβ–Ž | 26/195 [00:06<00:26, 6.34it/s] [2024-05-08 13:43:43] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
13%|β–ˆβ–Ž | 26/195 [00:06<00:26, 6.34it/s] 14%|β–ˆβ– | 27/195 [00:06<00:35, 4.75it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32
14%|β–ˆβ– | 27/195 [00:06<00:35, 4.75it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
14%|β–ˆβ– | 27/195 [00:06<00:35, 4.75it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
14%|β–ˆβ– | 27/195 [00:06<00:35, 4.75it/s] 15%|β–ˆβ–Œ | 30/195 [00:06<00:28, 5.85it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32
15%|β–ˆβ–Œ | 30/195 [00:06<00:28, 5.85it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
15%|β–ˆβ–Œ | 30/195 [00:06<00:28, 5.85it/s] 16%|β–ˆβ–‹ | 32/195 [00:07<00:25, 6.41it/s] [2024-05-08 13:43:44] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
16%|β–ˆβ–‹ | 32/195 [00:07<00:25, 6.41it/s] 17%|β–ˆβ–‹ | 33/195 [00:07<00:33, 4.78it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32
17%|β–ˆβ–‹ | 33/195 [00:07<00:33, 4.78it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
17%|β–ˆβ–‹ | 33/195 [00:07<00:33, 4.78it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
17%|β–ˆβ–‹ | 33/195 [00:07<00:33, 4.78it/s] 18%|β–ˆβ–Š | 36/195 [00:07<00:27, 5.88it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32
18%|β–ˆβ–Š | 36/195 [00:07<00:27, 5.88it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
18%|β–ˆβ–Š | 36/195 [00:07<00:27, 5.88it/s] 19%|β–ˆβ–‰ | 38/195 [00:08<00:24, 6.43it/s] [2024-05-08 13:43:45] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
19%|β–ˆβ–‰ | 38/195 [00:08<00:24, 6.43it/s] 20%|β–ˆβ–ˆ | 39/195 [00:08<00:32, 4.80it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32
20%|β–ˆβ–ˆ | 39/195 [00:08<00:32, 4.80it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
20%|β–ˆβ–ˆ | 39/195 [00:08<00:32, 4.80it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
20%|β–ˆβ–ˆ | 39/195 [00:08<00:32, 4.80it/s] 22%|β–ˆβ–ˆβ– | 42/195 [00:08<00:25, 5.90it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32
22%|β–ˆβ–ˆβ– | 42/195 [00:08<00:25, 5.90it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
22%|β–ˆβ–ˆβ– | 42/195 [00:08<00:25, 5.90it/s] 23%|β–ˆβ–ˆβ–Ž | 44/195 [00:09<00:23, 6.44it/s] [2024-05-08 13:43:46] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
23%|β–ˆβ–ˆβ–Ž | 44/195 [00:09<00:23, 6.44it/s] 23%|β–ˆβ–ˆβ–Ž | 45/195 [00:09<00:31, 4.81it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32
23%|β–ˆβ–ˆβ–Ž | 45/195 [00:09<00:31, 4.81it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
23%|β–ˆβ–ˆβ–Ž | 45/195 [00:09<00:31, 4.81it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
23%|β–ˆβ–ˆβ–Ž | 45/195 [00:09<00:31, 4.81it/s] 25%|β–ˆβ–ˆβ– | 48/195 [00:10<00:24, 5.90it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32
25%|β–ˆβ–ˆβ– | 48/195 [00:10<00:24, 5.90it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
25%|β–ˆβ–ˆβ– | 48/195 [00:10<00:24, 5.90it/s] 26%|β–ˆβ–ˆβ–Œ | 50/195 [00:10<00:22, 6.44it/s] [2024-05-08 13:43:47] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
26%|β–ˆβ–ˆβ–Œ | 50/195 [00:10<00:22, 6.44it/s] 26%|β–ˆβ–ˆβ–Œ | 51/195 [00:10<00:29, 4.80it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32
26%|β–ˆβ–ˆβ–Œ | 51/195 [00:10<00:29, 4.80it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
26%|β–ˆβ–ˆβ–Œ | 51/195 [00:10<00:29, 4.80it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
26%|β–ˆβ–ˆβ–Œ | 51/195 [00:10<00:29, 4.80it/s] 28%|β–ˆβ–ˆβ–Š | 54/195 [00:11<00:23, 5.89it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32
28%|β–ˆβ–ˆβ–Š | 54/195 [00:11<00:23, 5.89it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
28%|β–ˆβ–ˆβ–Š | 54/195 [00:11<00:23, 5.89it/s] 29%|β–ˆβ–ˆβ–Š | 56/195 [00:11<00:21, 6.44it/s] [2024-05-08 13:43:48] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
29%|β–ˆβ–ˆβ–Š | 56/195 [00:11<00:21, 6.44it/s] 29%|β–ˆβ–ˆβ–‰ | 57/195 [00:11<00:28, 4.81it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32
29%|β–ˆβ–ˆβ–‰ | 57/195 [00:11<00:28, 4.81it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
29%|β–ˆβ–ˆβ–‰ | 57/195 [00:11<00:28, 4.81it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
29%|β–ˆβ–ˆβ–‰ | 57/195 [00:11<00:28, 4.81it/s] 31%|β–ˆβ–ˆβ–ˆ | 60/195 [00:12<00:22, 5.89it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32
31%|β–ˆβ–ˆβ–ˆ | 60/195 [00:12<00:22, 5.89it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
31%|β–ˆβ–ˆβ–ˆ | 60/195 [00:12<00:22, 5.89it/s] 32%|β–ˆβ–ˆβ–ˆβ– | 62/195 [00:12<00:20, 6.38it/s] [2024-05-08 13:43:49] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
32%|β–ˆβ–ˆβ–ˆβ– | 62/195 [00:12<00:20, 6.38it/s] 32%|β–ˆβ–ˆβ–ˆβ– | 63/195 [00:12<00:27, 4.74it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32
32%|β–ˆβ–ˆβ–ˆβ– | 63/195 [00:12<00:27, 4.74it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
32%|β–ˆβ–ˆβ–ˆβ– | 63/195 [00:12<00:27, 4.74it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
32%|β–ˆβ–ˆβ–ˆβ– | 63/195 [00:12<00:27, 4.74it/s] 34%|β–ˆβ–ˆβ–ˆβ– | 66/195 [00:13<00:22, 5.84it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32
34%|β–ˆβ–ˆβ–ˆβ– | 66/195 [00:13<00:22, 5.84it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpom_oz7t5/repo/model-00002-of-00002.safetensors
34%|β–ˆβ–ˆβ–ˆβ– | 66/195 [00:13<00:22, 5.84it/s] [2024-05-08 13:43:50] INFO huggingface_loader.py:184: Loading HF parameters from: /tmp/tmpom_oz7t5/repo/model-00001-of-00002.safetensors
34%|β–ˆβ–ˆβ–ˆβ– | 66/195 [00:13<00:22, 5.84it/s] [2024-05-08 13:43:51] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.embd.weight", shape: (32064, 3072), dtype: float32
34%|β–ˆβ–ˆβ–ˆβ– | 66/195 [00:13<00:22, 5.84it/s] 35%|β–ˆβ–ˆβ–ˆβ– | 68/195 [00:14<00:42, 3.02it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32
35%|β–ˆβ–ˆβ–ˆβ– | 68/195 [00:14<00:42, 3.02it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
35%|β–ˆβ–ˆβ–ˆβ– | 68/195 [00:14<00:42, 3.02it/s] 36%|β–ˆβ–ˆβ–ˆβ–Œ | 70/195 [00:14<00:33, 3.71it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
36%|β–ˆβ–ˆβ–ˆβ–Œ | 70/195 [00:14<00:33, 3.71it/s] 36%|β–ˆβ–ˆβ–ˆβ–‹ | 71/195 [00:15<00:37, 3.30it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32
36%|β–ˆβ–ˆβ–ˆβ–‹ | 71/195 [00:15<00:37, 3.30it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
36%|β–ˆβ–ˆβ–ˆβ–‹ | 71/195 [00:15<00:37, 3.30it/s] [2024-05-08 13:43:52] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
36%|β–ˆβ–ˆβ–ˆβ–‹ | 71/195 [00:15<00:37, 3.30it/s] 38%|β–ˆβ–ˆβ–ˆβ–Š | 74/195 [00:15<00:26, 4.51it/s] [2024-05-08 13:43:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32
38%|β–ˆβ–ˆβ–ˆβ–Š | 74/195 [00:15<00:26, 4.51it/s] [2024-05-08 13:43:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
38%|β–ˆβ–ˆβ–ˆβ–Š | 74/195 [00:15<00:26, 4.51it/s] 39%|β–ˆβ–ˆβ–ˆβ–‰ | 76/195 [00:15<00:22, 5.23it/s] [2024-05-08 13:43:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
39%|β–ˆβ–ˆβ–ˆβ–‰ | 76/195 [00:15<00:22, 5.23it/s] 39%|β–ˆβ–ˆβ–ˆβ–‰ | 77/195 [00:16<00:28, 4.16it/s] [2024-05-08 13:43:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32
39%|β–ˆβ–ˆβ–ˆβ–‰ | 77/195 [00:16<00:28, 4.16it/s] [2024-05-08 13:43:53] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
39%|β–ˆβ–ˆβ–ˆβ–‰ | 77/195 [00:16<00:28, 4.16it/s] [2024-05-08 13:43:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
39%|β–ˆβ–ˆβ–ˆβ–‰ | 77/195 [00:16<00:28, 4.16it/s] 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 80/195 [00:16<00:21, 5.31it/s] [2024-05-08 13:43:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32
41%|β–ˆβ–ˆβ–ˆβ–ˆ | 80/195 [00:16<00:21, 5.31it/s] [2024-05-08 13:43:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
41%|β–ˆβ–ˆβ–ˆβ–ˆ | 80/195 [00:16<00:21, 5.31it/s] 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 82/195 [00:17<00:19, 5.92it/s] [2024-05-08 13:43:54] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 82/195 [00:17<00:19, 5.92it/s] 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 83/195 [00:17<00:24, 4.50it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32
43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 83/195 [00:17<00:24, 4.50it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 83/195 [00:17<00:24, 4.50it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 83/195 [00:17<00:24, 4.50it/s] 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 86/195 [00:17<00:19, 5.62it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32
44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 86/195 [00:17<00:19, 5.62it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 86/195 [00:17<00:19, 5.62it/s] 45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 88/195 [00:18<00:17, 6.25it/s] [2024-05-08 13:43:55] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 88/195 [00:18<00:17, 6.25it/s] 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 89/195 [00:18<00:22, 4.73it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32
46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 89/195 [00:18<00:22, 4.73it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 89/195 [00:18<00:22, 4.73it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 89/195 [00:18<00:22, 4.73it/s] 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 92/195 [00:18<00:17, 5.90it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32
47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 92/195 [00:18<00:17, 5.90it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 92/195 [00:18<00:17, 5.90it/s] 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 94/195 [00:19<00:15, 6.49it/s] [2024-05-08 13:43:56] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 94/195 [00:19<00:15, 6.49it/s] 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 95/195 [00:19<00:20, 4.85it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32
49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 95/195 [00:19<00:20, 4.85it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 95/195 [00:19<00:20, 4.85it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 95/195 [00:19<00:20, 4.85it/s] 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 98/195 [00:19<00:16, 6.01it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32
50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 98/195 [00:19<00:16, 6.01it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 98/195 [00:19<00:16, 6.01it/s] 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 100/195 [00:20<00:14, 6.57it/s] [2024-05-08 13:43:57] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 100/195 [00:20<00:14, 6.57it/s] 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 101/195 [00:20<00:19, 4.88it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32
52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 101/195 [00:20<00:19, 4.88it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 101/195 [00:20<00:19, 4.88it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 101/195 [00:20<00:19, 4.88it/s] 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 104/195 [00:20<00:15, 6.04it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32
53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 104/195 [00:20<00:15, 6.04it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 104/195 [00:20<00:15, 6.04it/s] 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 106/195 [00:21<00:13, 6.61it/s] [2024-05-08 13:43:58] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 106/195 [00:21<00:13, 6.61it/s] 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 107/195 [00:21<00:17, 4.90it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32
55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 107/195 [00:21<00:17, 4.90it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 107/195 [00:21<00:17, 4.90it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 107/195 [00:21<00:17, 4.90it/s] 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 110/195 [00:21<00:14, 6.03it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32
56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 110/195 [00:21<00:14, 6.03it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 110/195 [00:21<00:14, 6.03it/s] 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 112/195 [00:22<00:12, 6.54it/s] [2024-05-08 13:43:59] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 112/195 [00:22<00:12, 6.54it/s] 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 113/195 [00:22<00:17, 4.79it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32
58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 113/195 [00:22<00:17, 4.79it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 113/195 [00:22<00:17, 4.79it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 113/195 [00:22<00:17, 4.79it/s] 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 116/195 [00:23<00:13, 5.93it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32
59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 116/195 [00:23<00:13, 5.93it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 116/195 [00:23<00:13, 5.93it/s] 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 118/195 [00:23<00:11, 6.51it/s] [2024-05-08 13:44:00] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 118/195 [00:23<00:11, 6.51it/s] 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 119/195 [00:23<00:15, 4.86it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32
61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 119/195 [00:23<00:15, 4.86it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 119/195 [00:23<00:15, 4.86it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 119/195 [00:23<00:15, 4.86it/s] 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 122/195 [00:24<00:12, 6.02it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32
63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 122/195 [00:24<00:12, 6.02it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 122/195 [00:24<00:12, 6.02it/s] 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 124/195 [00:24<00:10, 6.59it/s] [2024-05-08 13:44:01] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 124/195 [00:24<00:10, 6.59it/s] 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 125/195 [00:24<00:14, 4.89it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32
64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 125/195 [00:24<00:14, 4.89it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 125/195 [00:24<00:14, 4.89it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 125/195 [00:24<00:14, 4.89it/s] 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 128/195 [00:25<00:11, 6.05it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32
66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 128/195 [00:25<00:11, 6.05it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 128/195 [00:25<00:11, 6.05it/s] 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 130/195 [00:25<00:09, 6.61it/s] [2024-05-08 13:44:02] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 130/195 [00:25<00:09, 6.61it/s] 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 131/195 [00:25<00:13, 4.90it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32
67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 131/195 [00:25<00:13, 4.90it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 131/195 [00:25<00:13, 4.90it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 131/195 [00:25<00:13, 4.90it/s] 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 134/195 [00:26<00:10, 6.06it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32
69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 134/195 [00:26<00:10, 6.06it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 134/195 [00:26<00:10, 6.06it/s] 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 136/195 [00:26<00:08, 6.63it/s] [2024-05-08 13:44:03] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 136/195 [00:26<00:08, 6.63it/s] 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 137/195 [00:26<00:11, 4.91it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32
70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 137/195 [00:26<00:11, 4.91it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 137/195 [00:26<00:11, 4.91it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 137/195 [00:26<00:11, 4.91it/s] 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 140/195 [00:27<00:09, 6.05it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32
72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 140/195 [00:27<00:09, 6.05it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 140/195 [00:27<00:09, 6.05it/s] 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 142/195 [00:27<00:08, 6.60it/s] [2024-05-08 13:44:04] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 142/195 [00:27<00:08, 6.60it/s] 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 143/195 [00:27<00:10, 4.88it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32
73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 143/195 [00:27<00:10, 4.88it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 143/195 [00:27<00:10, 4.88it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 143/195 [00:27<00:10, 4.88it/s] 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 146/195 [00:28<00:08, 6.03it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32
75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 146/195 [00:28<00:08, 6.03it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 146/195 [00:28<00:08, 6.03it/s] 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 148/195 [00:28<00:07, 6.58it/s] [2024-05-08 13:44:05] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 148/195 [00:28<00:07, 6.58it/s] 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 149/195 [00:28<00:09, 4.85it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32
76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 149/195 [00:28<00:09, 4.85it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 149/195 [00:28<00:09, 4.85it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 149/195 [00:28<00:09, 4.85it/s] 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 152/195 [00:29<00:07, 6.00it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 152/195 [00:29<00:07, 6.00it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32
78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 152/195 [00:29<00:07, 6.00it/s] [2024-05-08 13:44:06] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 152/195 [00:29<00:07, 6.00it/s] 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 155/195 [00:29<00:05, 6.97it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 155/195 [00:29<00:05, 6.97it/s] 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 156/195 [00:30<00:07, 5.22it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32
80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 156/195 [00:30<00:07, 5.22it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 156/195 [00:30<00:07, 5.22it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 156/195 [00:30<00:07, 5.22it/s] 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 159/195 [00:30<00:05, 6.24it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32
82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 159/195 [00:30<00:05, 6.24it/s] [2024-05-08 13:44:07] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 159/195 [00:30<00:05, 6.24it/s] 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 161/195 [00:30<00:05, 6.75it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 161/195 [00:30<00:05, 6.75it/s] 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 162/195 [00:31<00:06, 5.02it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32
83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 162/195 [00:31<00:06, 5.02it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 162/195 [00:31<00:06, 5.02it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 162/195 [00:31<00:06, 5.02it/s] 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 165/195 [00:31<00:04, 6.13it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32
85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 165/195 [00:31<00:04, 6.13it/s] [2024-05-08 13:44:08] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 165/195 [00:31<00:04, 6.13it/s] 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 167/195 [00:31<00:04, 6.67it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 167/195 [00:31<00:04, 6.67it/s] 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 168/195 [00:32<00:05, 4.95it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32
86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 168/195 [00:32<00:05, 4.95it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 168/195 [00:32<00:05, 4.95it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 168/195 [00:32<00:05, 4.95it/s] 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 171/195 [00:32<00:03, 6.09it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32
88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 171/195 [00:32<00:03, 6.09it/s] [2024-05-08 13:44:09] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 171/195 [00:32<00:03, 6.09it/s] 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 173/195 [00:32<00:03, 6.64it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 173/195 [00:32<00:03, 6.64it/s] 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 174/195 [00:33<00:04, 4.92it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32
89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 174/195 [00:33<00:04, 4.92it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 174/195 [00:33<00:04, 4.92it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 174/195 [00:33<00:04, 4.92it/s] 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 177/195 [00:33<00:02, 6.07it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32
91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 177/195 [00:33<00:02, 6.07it/s] [2024-05-08 13:44:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 177/195 [00:33<00:02, 6.07it/s] 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 179/195 [00:33<00:02, 6.63it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 179/195 [00:33<00:02, 6.63it/s] 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 180/195 [00:34<00:03, 4.91it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32
92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 180/195 [00:34<00:03, 4.91it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 180/195 [00:34<00:03, 4.91it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 180/195 [00:34<00:03, 4.91it/s] 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 183/195 [00:34<00:01, 6.07it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32
94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 183/195 [00:34<00:01, 6.07it/s] [2024-05-08 13:44:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 183/195 [00:34<00:01, 6.07it/s] 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 185/195 [00:34<00:01, 6.63it/s] [2024-05-08 13:44:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 185/195 [00:34<00:01, 6.63it/s] 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 186/195 [00:35<00:01, 4.92it/s] [2024-05-08 13:44:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32
95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 186/195 [00:35<00:01, 4.92it/s] [2024-05-08 13:44:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 186/195 [00:35<00:01, 4.92it/s] [2024-05-08 13:44:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 186/195 [00:35<00:01, 4.92it/s] 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 189/195 [00:35<00:00, 6.07it/s] [2024-05-08 13:44:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32
97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 189/195 [00:35<00:00, 6.07it/s] [2024-05-08 13:44:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mlp.down_proj.weight", shape: (3072, 8192), dtype: float32
97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 189/195 [00:35<00:00, 6.07it/s] 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 191/195 [00:35<00:00, 6.64it/s] [2024-05-08 13:44:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.weight", shape: (16384, 3072), dtype: float32
98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 191/195 [00:35<00:00, 6.64it/s] 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 192/195 [00:36<00:00, 4.92it/s] [2024-05-08 13:44:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32
98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 192/195 [00:36<00:00, 4.92it/s] [2024-05-08 13:44:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mixer.out_proj.weight", shape: (3072, 3072), dtype: float32
98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 192/195 [00:36<00:00, 4.92it/s] [2024-05-08 13:44:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.mixer.qkv_proj.weight", shape: (9216, 3072), dtype: float32
98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 192/195 [00:36<00:00, 4.92it/s] 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 195/195 [00:36<00:00, 6.07it/s] 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 195/195 [00:36<00:00, 5.34it/s]
[2024-05-08 13:44:14] INFO huggingface_loader.py:196: Unloading HF weight file: /tmp/tmpom_oz7t5/repo/model-00001-of-00002.safetensors
[2024-05-08 13:44:14] INFO stats.py:76: Time usage: HF loading: 1.466 sec; Pre-quantization mapping: 1.680 sec; Quantization: 0.000 sec
[2024-05-08 13:44:14] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
[2024-05-08 13:44:14] INFO convert_weight.py:155: Parameter size after quantization: 14.235 GB
[2024-05-08 13:44:14] INFO convert_weight.py:160: Total parameters: 3,821,079,552
[2024-05-08 13:44:14] INFO convert_weight.py:161: Bits per parameter: 32.000
[2024-05-08 13:44:14] INFO convert_weight.py:166: Saved to directory: /tmp/tmpbu0nfi81
All finished, 130 total shards committed, record saved to /tmp/tmpbu0nfi81/ndarray-cache.json
Also saved a bf16 record to /tmp/tmpbu0nfi81/ndarray-cache-b16.json