OCR失败，会出现RuntimeError: Input type (c10::BFloat16) and bias type (float) should be the same，已经用了最新的docker版本

[tozhouht]

return forward_call(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/.cache/huggingface/modules/transformers_modules/deepseek-ai/DeepSeek-OCR/1e3401a3d4603e9e71ea0ec850bfead602191ec4/modeling_deepseekocr.py", line 423, in forward

local_features_1 = sam_model(patches)

                   ^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl

return forward_call(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/.cache/huggingface/modules/transformers_modules/deepseek-ai/DeepSeek-OCR/1e3401a3d4603e9e71ea0ec850bfead602191ec4/deepencoder.py", line 699, in forward

x = self.patch_embed(x)

    ^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl

return forward_call(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/.cache/huggingface/modules/transformers_modules/deepseek-ai/DeepSeek-OCR/1e3401a3d4603e9e71ea0ec850bfead602191ec4/deepencoder.py", line 999, in forward

x = self.proj(x)

    ^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py", line 1786, in _call_impl

return forward_call(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/conv.py", line 548, in forward

return self._conv_forward(input, self.weight, self.bias)

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/local/lib/python3.12/dist-packages/torch/nn/modules/conv.py", line 543, in _conv_forward

return F.conv2d(

       ^^^^^^^^^

RuntimeError: Input type (c10::BFloat16) and bias type (float) should be the same

[zhanghanwei2008]

也碰到同样的问题，只用cpu计算就会有这个错误？ RuntimeError: Input type (c10::BFloat16) and bias type (float) should be the same