runtime error
Exit code: 1. Reason: s/base.py", line 171, in preprocess_model self._process_model_before_weight_loading(model, **kwargs) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/quantizers/quantizer_awq.py", line 74, in _process_model_before_weight_loading model = replace_with_awq_linear( model, ...<2 lines>... device_map=kwargs.get("device_map"), ) File "/usr/local/lib/python3.13/site-packages/transformers/integrations/awq.py", line 97, in replace_with_awq_linear new_module = target_cls( bits=quantization_config.bits, ...<7 lines>... register_buffers=True, ) File "/usr/local/lib/python3.13/site-packages/gptqmodel/nn_modules/qlinear/gemm_awq_triton.py", line 143, in __init__ super().__init__( ~~~~~~~~~~~~~~~~^ bits=bits, ^^^^^^^^^^ ...<9 lines>... register_buffers=register_buffers, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ **kwargs) ^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/gptqmodel/nn_modules/qlinear/__init__.py", line 1415, in __init__ super().__init__(bias=bias, register_buffers=False, **kwargs) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/gptqmodel/nn_modules/qlinear/__init__.py", line 575, in __init__ super().__init__(*args, pack_dtype=pack_dtype, **kwargs) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/gptqmodel/nn_modules/qlinear/__init__.py", line 478, in __init__ super().__init__( ~~~~~~~~~~~~~~~~^ bits=bits, ^^^^^^^^^^ ...<16 lines>... **kwargs, ^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/gptqmodel/nn_modules/qlinear/__init__.py", line 100, in __init__ raise err NotImplementedError: <class 'gptqmodel.nn_modules.qlinear.gemm_awq_triton.AwqGEMMTritonLinear'>: `in_features`: 3420 must be divisible by `group_size: 128`.
Container logs:
Fetching error logs...