runtime error

Exit code: 1. Reason: k/2.10k [00:00<00:00, 8.61MB/s] tokenizer.json: 0%| | 0.00/32.2M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 32.2M/32.2M [00:00<00:00, 76.7MB/s] chat_template.jinja: 0%| | 0.00/16.3k [00:00<?, ?B/s] chat_template.jinja: 100%|██████████| 16.3k/16.3k [00:00<00:00, 22.7MB/s] Traceback (most recent call last): File "/app/app.py", line 36, in <module> model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="cpu") File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 394, in from_pretrained return model_class.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~^ pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4130, in from_pretrained hf_quantizer, config, device_map = get_hf_quantizer( ~~~~~~~~~~~~~~~~^ config, quantization_config, device_map, weights_only, user_agent ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 323, in get_hf_quantizer if pre_quantized and not AutoHfQuantizer.supports_quant_method(config.quantization_config): ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 275, in supports_quant_method raise ValueError( "The model's quantization config from the arguments has no `quant_method` attribute. Make sure that the model has been correctly quantized" ) ValueError: The model's quantization config from the arguments has no `quant_method` attribute. Make sure that the model has been correctly quantized

Container logs: