Initial commit

5cc249e verified 10 months ago

129 kB

	/home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat gen_config /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4 --quantization q0f16 --conv-template chatml --output /tmp/tmpalrsn161
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
	setattr(self, word, getattr(machar, word).flat[0])
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
	return self._float_to_str(self.smallest_subnormal)
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/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/cfruan/.conda/envs/mlc-source-311/lib/python3.11/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)
	[2024-01-16 09:48:29] INFO auto_config.py:115: [92mFound[0m model configuration: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/config.json
	[2024-01-16 09:48:29] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-01-16 09:48:29] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048)
	[2024-01-16 09:48:29] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (2048)
	[2024-01-16 09:48:29] INFO gen_config.py:117: [config.json] Setting [1mbos_token_id[0m: 1
	[2024-01-16 09:48:29] INFO gen_config.py:117: [config.json] Setting [1meos_token_id[0m: 2
	[2024-01-16 09:48:29] INFO gen_config.py:129: [92mFound[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/tokenizer.model. Copying to [1m/tmp/tmpalrsn161/tokenizer.model[0m
	[2024-01-16 09:48:29] INFO gen_config.py:129: [92mFound[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/tokenizer.json. Copying to [1m/tmp/tmpalrsn161/tokenizer.json[0m
	[2024-01-16 09:48:29] INFO gen_config.py:131: [91mNot found[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/vocab.json
	[2024-01-16 09:48:29] INFO gen_config.py:131: [91mNot found[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/merges.txt
	[2024-01-16 09:48:29] INFO gen_config.py:129: [92mFound[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/added_tokens.json. Copying to [1m/tmp/tmpalrsn161/added_tokens.json[0m
	[2024-01-16 09:48:29] INFO gen_config.py:129: [92mFound[0m tokenizer config: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/tokenizer_config.json. Copying to [1m/tmp/tmpalrsn161/tokenizer_config.json[0m
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mpad_token_id[0m: 0
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mtemperature[0m: 0.7
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mrepetition_penalty[0m: 1.0
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mtop_p[0m: 0.95
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mmean_gen_len[0m: 128
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mmax_gen_len[0m: 512
	[2024-01-16 09:48:29] INFO gen_config.py:70: [System default] Setting [1mshift_fill_factor[0m: 0.3
	[2024-01-16 09:48:29] INFO gen_config.py:159: Dumping configuration file to: [1m/tmp/tmpalrsn161/mlc-chat-config.json[0m
	/home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat convert_weight /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4 --quantization q0f16 --source-format auto --output /tmp/tmpalrsn161
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
	setattr(self, word, getattr(machar, word).flat[0])
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float64'> type is zero.
	return self._float_to_str(self.smallest_subnormal)
	/home/cfruan/.conda/envs/mlc-source-311/lib/python3.11/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/cfruan/.conda/envs/mlc-source-311/lib/python3.11/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)
	[2024-01-16 09:48:30] INFO auto_config.py:115: [92mFound[0m model configuration: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/config.json
	[2024-01-16 09:48:30] INFO auto_device.py:76: [92mFound[0m device: cuda:0
	[2024-01-16 09:48:30] INFO auto_device.py:76: [92mFound[0m device: cuda:1
	[2024-01-16 09:48:31] INFO auto_device.py:85: [91mNot found[0m device: rocm:0
	[2024-01-16 09:48:31] INFO auto_device.py:85: [91mNot found[0m device: metal:0
	[2024-01-16 09:48:32] INFO auto_device.py:76: [92mFound[0m device: vulkan:0
	[2024-01-16 09:48:32] INFO auto_device.py:76: [92mFound[0m device: vulkan:1
	[2024-01-16 09:48:32] INFO auto_device.py:76: [92mFound[0m device: vulkan:2
	[2024-01-16 09:48:32] INFO auto_device.py:85: [91mNot found[0m device: opencl:0
	[2024-01-16 09:48:32] INFO auto_device.py:33: Using device: [1mcuda:0[0m
	[2024-01-16 09:48:32] INFO auto_weight.py:70: Finding weights in: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4
	[2024-01-16 09:48:32] INFO auto_weight.py:129: [92mFound[0m source weight format: huggingface-torch. Source configuration: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/pytorch_model.bin
	[2024-01-16 09:48:32] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/model.safetensors.index.json
	[2024-01-16 09:48:32] INFO auto_weight.py:106: Using source weight configuration: [1m/ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/pytorch_model.bin[0m. Use `--source` to override.
	[2024-01-16 09:48:32] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-torch[0m. Use `--source-format` to override.
	[2024-01-16 09:48:32] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
	[2024-01-16 09:48:32] INFO llama_model.py:51: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048)
	[2024-01-16 09:48:32] INFO llama_model.py:71: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (2048)
	[2024-01-16 09:48:36] INFO huggingface_loader.py:169: Loading HF parameters from: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/pytorch_model.bin
	[1mWeight conversion with arguments:[0m
	[1m--config[0m /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/config.json
	[1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
	[1m--model-type[0m llama
	[1m--device[0m cuda:0
	[1m--source[0m /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/pytorch_model.bin
	[1m--source-format[0m huggingface-torch
	[1m--output[0m /tmp/tmpalrsn161
	0%\| \| 0/135 [00:00<?, ?it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (32003, 2048), dtype: float16
	0%\| \| 0/135 [00:00<?, ?it/s] 1%\|█▏ \| 1/135 [00:00<01:13, 1.82it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	1%\|█▏ \| 1/135 [00:00<01:13, 1.82it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	1%\|█▏ \| 1/135 [00:00<01:13, 1.82it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	1%\|█▏ \| 1/135 [00:00<01:13, 1.82it/s] 3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:39] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	3%\|████▌ \| 4/135 [00:00<00:23, 5.57it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	3%\|████▌ \| 4/135 [00:01<00:23, 5.57it/s] 7%\|███████████▎ \| 10/135 [00:01<00:11, 10.53it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	7%\|███████████▎ \| 10/135 [00:01<00:11, 10.53it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	7%\|███████████▎ \| 10/135 [00:01<00:11, 10.53it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	7%\|███████████▎ \| 10/135 [00:01<00:11, 10.53it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	7%\|███████████▎ \| 10/135 [00:01<00:11, 10.53it/s] 10%\|███████████████▊ \| 14/135 [00:01<00:08, 14.12it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	10%\|███████████████▊ \| 14/135 [00:01<00:08, 14.12it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	10%\|███████████████▊ \| 14/135 [00:01<00:08, 14.12it/s] 12%\|██████████████████ \| 16/135 [00:01<00:10, 11.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	12%\|██████████████████ \| 16/135 [00:01<00:10, 11.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	12%\|██████████████████ \| 16/135 [00:01<00:10, 11.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	12%\|██████████████████ \| 16/135 [00:01<00:10, 11.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	12%\|██████████████████ \| 16/135 [00:01<00:10, 11.70it/s] 15%\|██████████████████████▌ \| 20/135 [00:01<00:07, 15.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	15%\|██████████████████████▌ \| 20/135 [00:01<00:07, 15.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	15%\|██████████████████████▌ \| 20/135 [00:01<00:07, 15.70it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	15%\|██████████████████████▌ \| 20/135 [00:02<00:07, 15.70it/s] 17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] [2024-01-16 09:48:40] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	17%\|█████████████████████████▉ \| 23/135 [00:02<00:08, 12.96it/s] 21%\|███████████████████████████████▌ \| 28/135 [00:02<00:07, 13.84it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	21%\|███████████████████████████████▌ \| 28/135 [00:02<00:07, 13.84it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	21%\|███████████████████████████████▌ \| 28/135 [00:02<00:07, 13.84it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	21%\|███████████████████████████████▌ \| 28/135 [00:02<00:07, 13.84it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	21%\|███████████████████████████████▌ \| 28/135 [00:02<00:07, 13.84it/s] 24%\|████████████████████████████████████ \| 32/135 [00:02<00:06, 16.53it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	24%\|████████████████████████████████████ \| 32/135 [00:02<00:06, 16.53it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	24%\|████████████████████████████████████ \| 32/135 [00:02<00:06, 16.53it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	24%\|████████████████████████████████████ \| 32/135 [00:02<00:06, 16.53it/s] 26%\|███████████████████████████████████████▍ \| 35/135 [00:02<00:07, 13.46it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	26%\|███████████████████████████████████████▍ \| 35/135 [00:02<00:07, 13.46it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	26%\|███████████████████████████████████████▍ \| 35/135 [00:02<00:07, 13.46it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	26%\|███████████████████████████████████████▍ \| 35/135 [00:02<00:07, 13.46it/s] [2024-01-16 09:48:41] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	26%\|███████████████████████████████████████▍ \| 35/135 [00:02<00:07, 13.46it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	26%\|███████████████████████████████████████▍ \| 35/135 [00:03<00:07, 13.46it/s] 30%\|█████████████████████████████████████████████ \| 40/135 [00:03<00:06, 14.65it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	30%\|█████████████████████████████████████████████ \| 40/135 [00:03<00:06, 14.65it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	30%\|█████████████████████████████████████████████ \| 40/135 [00:03<00:06, 14.65it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	30%\|█████████████████████████████████████████████ \| 40/135 [00:03<00:06, 14.65it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	30%\|█████████████████████████████████████████████ \| 40/135 [00:03<00:06, 14.65it/s] 33%\|█████████████████████████████████████████████████▌ \| 44/135 [00:03<00:05, 17.25it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	33%\|█████████████████████████████████████████████████▌ \| 44/135 [00:03<00:05, 17.25it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	33%\|█████████████████████████████████████████████████▌ \| 44/135 [00:03<00:05, 17.25it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	33%\|█████████████████████████████████████████████████▌ \| 44/135 [00:03<00:05, 17.25it/s] 35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	35%\|████████████████████████████████████████████████████▉ \| 47/135 [00:03<00:06, 14.63it/s] 39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:03<00:05, 14.18it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:03<00:05, 14.18it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:03<00:05, 14.18it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:03<00:05, 14.18it/s] [2024-01-16 09:48:42] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:04<00:05, 14.18it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:04<00:05, 14.18it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	39%\|██████████████████████████████████████████████████████████▌ \| 52/135 [00:04<00:05, 14.18it/s] 43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	43%\|█████████████████████████████████████████████████████████████████▎ \| 58/135 [00:04<00:04, 17.31it/s] 47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	47%\|████████████████████████████████████████████████████████████████████████ \| 64/135 [00:04<00:03, 19.85it/s] 52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	52%\|██████████████████████████████████████████████████████████████████████████████▊ \| 70/135 [00:04<00:03, 20.64it/s] 56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:04<00:02, 21.02it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:04<00:02, 21.02it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:04<00:02, 21.02it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:04<00:02, 21.02it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:05<00:02, 21.02it/s] [2024-01-16 09:48:43] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:05<00:02, 21.02it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	56%\|█████████████████████████████████████████████████████████████████████████████████████▌ \| 76/135 [00:05<00:02, 21.02it/s] 61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	61%\|████████████████████████████████████████████████████████████████████████████████████████████▎ \| 82/135 [00:05<00:02, 20.70it/s] 65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	65%\|███████████████████████████████████████████████████████████████████████████████████████████████████ \| 88/135 [00:05<00:02, 22.20it/s] 70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	70%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 94/135 [00:05<00:01, 23.21it/s] 74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:05<00:01, 24.18it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:05<00:01, 24.18it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:05<00:01, 24.18it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:05<00:01, 24.18it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:05<00:01, 24.18it/s] [2024-01-16 09:48:44] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:06<00:01, 24.18it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	74%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ \| 100/135 [00:06<00:01, 24.18it/s] 79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	79%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ \| 106/135 [00:06<00:01, 24.89it/s] 83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	83%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ \| 112/135 [00:06<00:00, 25.42it/s] 87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	87%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ \| 118/135 [00:06<00:00, 25.87it/s] 92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:45] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:06<00:00, 26.20it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16
	92%\|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ \| 124/135 [00:07<00:00, 26.20it/s] 96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16
	96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float16
	96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16
	96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float16
	96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] [2024-01-16 09:48:46] INFO huggingface_loader.py:129: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (32003, 2048), dtype: float16
	96%\|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ \| 130/135 [00:07<00:00, 25.83it/s] 100%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 135/135 [00:07<00:00, 20.73it/s] 100%\|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████\| 135/135 [00:07<00:00, 18.16it/s]
	[2024-01-16 09:48:46] INFO huggingface_loader.py:179: Unloading HF weight file: /ssd1/cfruan/models/TinyLlama-1.1B-Chat-v0.4/pytorch_model.bin
	[2024-01-16 09:48:46] INFO stats.py:71: [92mTime usage[0m: HF loading: 2.397 sec; Pre-quantization mapping: 6.585 sec; Quantization: 0.000 sec
	[2024-01-16 09:48:46] INFO stats.py:85: [92mRAM usage[0m: Peak RAM: 4.098 GB. Total bytes loaded from disk: 4.098 GB
	[2024-01-16 09:48:46] INFO convert_weight.py:119: [92mParameter size[0m after quantization: 2.049 GB
	[2024-01-16 09:48:46] INFO convert_weight.py:124: [92mTotal parameters[0m: 1,100,060,672
	[2024-01-16 09:48:46] INFO convert_weight.py:125: [92mBits per parameter[0m: 16.000
	Start storing to cache /tmp/tmpalrsn161
	[0001/0135] saving model.embed_tokens.weight [0002/0135] saving model.layers.0.self_attn.qkv_proj.weight [0003/0135] saving model.layers.0.self_attn.o_proj.weight [0004/0135] saving model.layers.0.mlp.gate_up_proj.weight [0005/0135] saving model.layers.0.mlp.down_proj.weight [0006/0135] saving model.layers.0.input_layernorm.weight [0007/0135] saving model.layers.0.post_attention_layernorm.weight [0008/0135] saving model.layers.1.self_attn.qkv_proj.weight [0009/0135] saving model.layers.1.self_attn.o_proj.weight [0010/0135] saving model.layers.1.mlp.gate_up_proj.weight [0011/0135] saving model.layers.1.mlp.down_proj.weight [0012/0135] saving model.layers.1.input_layernorm.weight [0013/0135] saving model.layers.1.post_attention_layernorm.weight [0014/0135] saving model.layers.2.self_attn.qkv_proj.weight [0015/0135] saving model.layers.2.self_attn.o_proj.weight [0016/0135] saving model.layers.2.mlp.gate_up_proj.weight [0017/0135] saving model.layers.2.mlp.down_proj.weight [0018/0135] saving model.layers.2.input_layernorm.weight [0019/0135] saving model.layers.2.post_attention_layernorm.weight [0020/0135] saving model.layers.3.self_attn.qkv_proj.weight [0021/0135] saving model.layers.3.self_attn.o_proj.weight [0022/0135] saving model.layers.3.mlp.gate_up_proj.weight [0023/0135] saving model.layers.3.mlp.down_proj.weight [0024/0135] saving model.layers.3.input_layernorm.weight [0025/0135] saving model.layers.3.post_attention_layernorm.weight [0026/0135] saving model.layers.4.self_attn.qkv_proj.weight [0027/0135] saving model.layers.4.self_attn.o_proj.weight [0028/0135] saving model.layers.4.mlp.gate_up_proj.weight [0029/0135] saving model.layers.4.mlp.down_proj.weight [0030/0135] saving model.layers.4.input_layernorm.weight [0031/0135] saving model.layers.4.post_attention_layernorm.weight [0032/0135] saving model.layers.5.self_attn.qkv_proj.weight [0033/0135] saving model.layers.5.self_attn.o_proj.weight [0034/0135] saving model.layers.5.mlp.gate_up_proj.weight [0035/0135] saving model.layers.5.mlp.down_proj.weight [0036/0135] saving model.layers.5.input_layernorm.weight [0037/0135] saving model.layers.5.post_attention_layernorm.weight [0038/0135] saving model.layers.6.self_attn.qkv_proj.weight [0039/0135] saving model.layers.6.self_attn.o_proj.weight [0040/0135] saving model.layers.6.mlp.gate_up_proj.weight [0041/0135] saving model.layers.6.mlp.down_proj.weight [0042/0135] saving model.layers.6.input_layernorm.weight [0043/0135] saving model.layers.6.post_attention_layernorm.weight [0044/0135] saving model.layers.7.self_attn.qkv_proj.weight [0045/0135] saving model.layers.7.self_attn.o_proj.weight [0046/0135] saving model.layers.7.mlp.gate_up_proj.weight [0047/0135] saving model.layers.7.mlp.down_proj.weight [0048/0135] saving model.layers.7.input_layernorm.weight [0049/0135] saving model.layers.7.post_attention_layernorm.weight [0050/0135] saving model.layers.8.self_attn.qkv_proj.weight [0051/0135] saving model.layers.8.self_attn.o_proj.weight [0052/0135] saving model.layers.8.mlp.gate_up_proj.weight [0053/0135] saving model.layers.8.mlp.down_proj.weight [0054/0135] saving model.layers.8.input_layernorm.weight [0055/0135] saving model.layers.8.post_attention_layernorm.weight [0056/0135] saving model.layers.9.self_attn.qkv_proj.weight [0057/0135] saving model.layers.9.self_attn.o_proj.weight [0058/0135] saving model.layers.9.mlp.gate_up_proj.weight [0059/0135] saving model.layers.9.mlp.down_proj.weight [0060/0135] saving model.layers.9.input_layernorm.weight [0061/0135] saving model.layers.9.post_attention_layernorm.weight [0062/0135] saving model.layers.10.self_attn.qkv_proj.weight [0063/0135] saving model.layers.10.self_attn.o_proj.weight [0064/0135] saving model.layers.10.mlp.gate_up_proj.weight [0065/0135] saving model.layers.10.mlp.down_proj.weight [0066/0135] saving model.layers.10.input_layernorm.weight [0067/0135] saving model.layers.10.post_attention_layernorm.weight [0068/0135] saving model.layers.11.self_attn.qkv_proj.weight [0069/0135] saving model.layers.11.self_attn.o_proj.weight [0070/0135] saving model.layers.11.mlp.gate_up_proj.weight [0071/0135] saving model.layers.11.mlp.down_proj.weight [0072/0135] saving model.layers.11.input_layernorm.weight [0073/0135] saving model.layers.11.post_attention_layernorm.weight [0074/0135] saving model.layers.12.self_attn.qkv_proj.weight [0075/0135] saving model.layers.12.self_attn.o_proj.weight [0076/0135] saving model.layers.12.mlp.gate_up_proj.weight [0077/0135] saving model.layers.12.mlp.down_proj.weight [0078/0135] saving model.layers.12.input_layernorm.weight [0079/0135] saving model.layers.12.post_attention_layernorm.weight [0080/0135] saving model.layers.13.self_attn.qkv_proj.weight [0081/0135] saving model.layers.13.self_attn.o_proj.weight [0082/0135] saving model.layers.13.mlp.gate_up_proj.weight [0083/0135] saving model.layers.13.mlp.down_proj.weight [0084/0135] saving model.layers.13.input_layernorm.weight [0085/0135] saving model.layers.13.post_attention_layernorm.weight [0086/0135] saving model.layers.14.self_attn.qkv_proj.weight [0087/0135] saving model.layers.14.self_attn.o_proj.weight [0088/0135] saving model.layers.14.mlp.gate_up_proj.weight [0089/0135] saving model.layers.14.mlp.down_proj.weight [0090/0135] saving model.layers.14.input_layernorm.weight [0091/0135] saving model.layers.14.post_attention_layernorm.weight [0092/0135] saving model.layers.15.self_attn.qkv_proj.weight [0093/0135] saving model.layers.15.self_attn.o_proj.weight [0094/0135] saving model.layers.15.mlp.gate_up_proj.weight [0095/0135] saving model.layers.15.mlp.down_proj.weight [0096/0135] saving model.layers.15.input_layernorm.weight [0097/0135] saving model.layers.15.post_attention_layernorm.weight [0098/0135] saving model.layers.16.self_attn.qkv_proj.weight [0099/0135] saving model.layers.16.self_attn.o_proj.weight [0100/0135] saving model.layers.16.mlp.gate_up_proj.weight [0101/0135] saving model.layers.16.mlp.down_proj.weight [0102/0135] saving model.layers.16.input_layernorm.weight [0103/0135] saving model.layers.16.post_attention_layernorm.weight [0104/0135] saving model.layers.17.self_attn.qkv_proj.weight [0105/0135] saving model.layers.17.self_attn.o_proj.weight [0106/0135] saving model.layers.17.mlp.gate_up_proj.weight [0107/0135] saving model.layers.17.mlp.down_proj.weight [0108/0135] saving model.layers.17.input_layernorm.weight [0109/0135] saving model.layers.17.post_attention_layernorm.weight [0110/0135] saving model.layers.18.self_attn.qkv_proj.weight [0111/0135] saving model.layers.18.self_attn.o_proj.weight [0112/0135] saving model.layers.18.mlp.gate_up_proj.weight [0113/0135] saving model.layers.18.mlp.down_proj.weight [0114/0135] saving model.layers.18.input_layernorm.weight [0115/0135] saving model.layers.18.post_attention_layernorm.weight [0116/0135] saving model.layers.19.self_attn.qkv_proj.weight [0117/0135] saving model.layers.19.self_attn.o_proj.weight [0118/0135] saving model.layers.19.mlp.gate_up_proj.weight [0119/0135] saving model.layers.19.mlp.down_proj.weight [0120/0135] saving model.layers.19.input_layernorm.weight [0121/0135] saving model.layers.19.post_attention_layernorm.weight [0122/0135] saving model.layers.20.self_attn.qkv_proj.weight [0123/0135] saving model.layers.20.self_attn.o_proj.weight [0124/0135] saving model.layers.20.mlp.gate_up_proj.weight [0125/0135] saving model.layers.20.mlp.down_proj.weight [0126/0135] saving model.layers.20.input_layernorm.weight [0127/0135] saving model.layers.20.post_attention_layernorm.weight [0128/0135] saving model.layers.21.self_attn.qkv_proj.weight [0129/0135] saving model.layers.21.self_attn.o_proj.weight [0130/0135] saving model.layers.21.mlp.gate_up_proj.weight[2024-01-16 09:48:51] INFO convert_weight.py:141: Saved to directory: [1m/tmp/tmpalrsn161[0m
	[0131/0135] saving model.layers.21.mlp.down_proj.weight [0132/0135] saving model.layers.21.input_layernorm.weight [0133/0135] saving model.layers.21.post_attention_layernorm.weight [0134/0135] saving model.norm.weight [0135/0135] saving lm_head.weight
	All finished, 57 total shards committed, record saved to /tmp/tmpalrsn161/ndarray-cache.json