/home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat gen_config /ssd1/cfruan/models/phi-2 --quantization q0f32 --conv-template phi-2 --output /tmp/tmpuqhwa6i9 /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 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 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 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 type is zero. return self._float_to_str(self.smallest_subnormal) [2024-01-19 17:42:48] INFO auto_config.py:115: Found model configuration: /ssd1/cfruan/models/phi-2/config.json [2024-01-19 17:42:48] INFO auto_config.py:153: Found model type: phi-msft. Use `--model-type` to override. [2024-01-19 17:42:48] INFO phi_model.py:116: context_window_size not found in config.json. Falling back to n_positions (2048) [2024-01-19 17:42:48] INFO gen_config.py:131: Not found tokenizer config: /ssd1/cfruan/models/phi-2/tokenizer.model [2024-01-19 17:42:48] INFO gen_config.py:129: Found tokenizer config: /ssd1/cfruan/models/phi-2/tokenizer.json. Copying to /tmp/tmpuqhwa6i9/tokenizer.json [2024-01-19 17:42:48] INFO gen_config.py:129: Found tokenizer config: /ssd1/cfruan/models/phi-2/vocab.json. Copying to /tmp/tmpuqhwa6i9/vocab.json [2024-01-19 17:42:48] INFO gen_config.py:129: Found tokenizer config: /ssd1/cfruan/models/phi-2/merges.txt. Copying to /tmp/tmpuqhwa6i9/merges.txt [2024-01-19 17:42:48] INFO gen_config.py:129: Found tokenizer config: /ssd1/cfruan/models/phi-2/added_tokens.json. Copying to /tmp/tmpuqhwa6i9/added_tokens.json [2024-01-19 17:42:48] INFO gen_config.py:129: Found tokenizer config: /ssd1/cfruan/models/phi-2/tokenizer_config.json. Copying to /tmp/tmpuqhwa6i9/tokenizer_config.json [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting pad_token_id: 0 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting bos_token_id: 1 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting eos_token_id: 2 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting temperature: 0.7 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting repetition_penalty: 1.0 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting top_p: 0.95 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting mean_gen_len: 128 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting max_gen_len: 512 [2024-01-19 17:42:48] INFO gen_config.py:70: [System default] Setting shift_fill_factor: 0.3 [2024-01-19 17:42:48] INFO gen_config.py:159: Dumping configuration file to: /tmp/tmpuqhwa6i9/mlc-chat-config.json /home/cfruan/.conda/envs/mlc-source-311/bin/python -m mlc_chat convert_weight /ssd1/cfruan/models/phi-2 --quantization q0f32 --source-format auto --output /tmp/tmpuqhwa6i9 /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 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 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 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 type is zero. return self._float_to_str(self.smallest_subnormal) [2024-01-19 17:42:49] INFO auto_config.py:115: Found model configuration: /ssd1/cfruan/models/phi-2/config.json [2024-01-19 17:42:50] INFO auto_device.py:76: Found device: cuda:0 [2024-01-19 17:42:50] INFO auto_device.py:76: Found device: cuda:1 [2024-01-19 17:42:50] INFO auto_device.py:85: Not found device: rocm:0 [2024-01-19 17:42:50] INFO auto_device.py:85: Not found device: metal:0 [2024-01-19 17:42:51] INFO auto_device.py:76: Found device: vulkan:0 [2024-01-19 17:42:51] INFO auto_device.py:76: Found device: vulkan:1 [2024-01-19 17:42:51] INFO auto_device.py:76: Found device: vulkan:2 [2024-01-19 17:42:51] INFO auto_device.py:85: Not found device: opencl:0 [2024-01-19 17:42:51] INFO auto_device.py:33: Using device: cuda:0 [2024-01-19 17:42:51] INFO auto_weight.py:70: Finding weights in: /ssd1/cfruan/models/phi-2 [2024-01-19 17:42:51] INFO auto_weight.py:136: Not found Huggingface PyTorch [2024-01-19 17:42:51] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /ssd1/cfruan/models/phi-2/model.safetensors.index.json [2024-01-19 17:42:51] INFO auto_weight.py:106: Using source weight configuration: /ssd1/cfruan/models/phi-2/model.safetensors.index.json. Use `--source` to override. [2024-01-19 17:42:51] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-01-19 17:42:51] INFO auto_config.py:153: Found model type: phi-msft. Use `--model-type` to override. [2024-01-19 17:42:51] INFO phi_model.py:116: context_window_size not found in config.json. Falling back to n_positions (2048) Weight conversion with arguments: --config /ssd1/cfruan/models/phi-2/config.json --quantization NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32') --model-type phi-msft --device cuda:0 --source /ssd1/cfruan/models/phi-2/model.safetensors.index.json --source-format huggingface-safetensor --output /tmp/tmpuqhwa6i9 0%| | 0/325 [00:00