ModelScope中，在使用awq量化qwen2 72b的时候遇到了以上问题，怎么解决？
"Traceback (most recent call last):
File ""/root/swift/swift_new/lib/python3.11/site-packages/swift/cli/export.py"", line 5, in
export_main()
File ""/root/swift/swift_new/lib/python3.11/site-packages/swift/utils/run_utils.py"", line 27, in x_main
result = llm_x(args, kwargs)
^^^^^^^^^^^^^^^^^^^^^
File ""/root/swift/swift_new/lib/python3.11/site-packages/swift/llm/export.py"", line 109, in llm_export
awq_model_quantize(model, template.tokenizer)
File ""/root/swift/swift_new/lib/python3.11/site-packages/swift/llm/export.py"", line 71, in awq_model_quantize
awq_model.quantize(tokenizer, quant_config=quant_config)
File ""/root/swift/swift_new/lib/python3.11/site-packages/torch/utils/_contextlib.py"", line 115, in decorate_context
return func(*args, kwargs)
^^^^^^^^^^^^^^^^^^^^^
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/models/base.py"", line 186, in quantize
self.quantizer.quantize()
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/quantize/quantizer.py"", line 156, in quantize
scales_list = [
^
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/quantize/quantizer.py"", line 157, in
self._search_best_scale(self.modules[i], layer)
File ""/root/swift/swift_new/lib/python3.11/site-packages/torch/utils/_contextlib.py"", line 115, in decorate_context
return func(*args, kwargs)
^^^^^^^^^^^^^^^^^^^^^
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/quantize/quantizer.py"", line 277, in _search_best_scale
best_scales = self._compute_best_scale(
^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/quantize/quantizer.py"", line 334, in _compute_best_scale
self.pseudo_quantize_tensor(fc.weight.data)[0] / scales_view
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/root/swift/swift_new/lib/python3.11/site-packages/awq/quantize/quantizer.py"", line 69, in pseudo_quantize_tensor
assert torch.isnan(w).sum() == 0
^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError ModelScope中，在使用awq量化qwen2 72b的时候遇到了以上问题，怎么解决？ "
ModelScope旨在打造下一代开源的模型即服务共享平台，为泛AI开发者提供灵活、易用、低成本的一站式模型服务产品，让模型应用更简单！欢迎加入技术交流群：微信公众号：魔搭ModelScope社区，钉钉群号：44837352