runtime error

Exit code: 1. Reason: kB/s] 2026-02-13 15:03:48.314 | INFO | __main__:load_models:143 - Loading XCodec2... config.json: 0%| | 0.00/222 [00:00<?, ?B/s] config.json: 100%|██████████| 222/222 [00:00<00:00, 1.24MB/s] You are using a model of type xcodec2 to instantiate a model of type bigcodec. This is not supported for all configurations of models and can yield errors. model.safetensors: 0%| | 0.00/3.29G [00:00<?, ?B/s] model.safetensors: 0%| | 4.67M/3.29G [00:01<11:54, 4.60MB/s] model.safetensors: 43%|████▎ | 1.41G/3.29G [00:02<00:02, 824MB/s]  model.safetensors: 98%|█████████▊| 3.22G/3.29G [00:03<00:00, 1.15GB/s] model.safetensors: 100%|██████████| 3.29G/3.29G [00:03<00:00, 1.00GB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 157, in <module> load_models() File "/home/user/app/app.py", line 144, in load_models codec_model = XCodec2Model.from_pretrained(XCODEC_MODEL_ID).eval().to(device) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4021, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/home/user/app/xcodec2/modeling_xcodec2.py", line 18, in __init__ self.semantic_model = Wav2Vec2BertModel.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3928, in from_pretrained device_map = check_and_set_device_map(device_map) # warn, error and fix the device map File "/usr/local/lib/python3.10/site-packages/transformers/integrations/accelerate.py", line 100, in check_and_set_device_map raise RuntimeError( RuntimeError: You are using `from_pretrained` with a meta device context manager or `torch.set_default_device('meta')`. This is an anti-pattern as `from_pretrained` wants to load existing weights. If you want to initialize an empty model on the meta device, use the context manager or global device with `from_config`, or `ModelClass(config)`

Container logs: