allenai

/

Molmo-7B-D-0924

like 159

The running machine is runpod's A40. (48G vram, 50G ram, 50GB storage)
I copy the example code and save it as test.py, then drag it on the runpod server.
Simply run it and get the error...

python test.py
Loading checkpoint shards: 100%|███████████████████████████████████████| 7/7 [00:07<00:00,  1.01s/it]
Traceback (most recent call last):
  File "/workspace/test.py", line 32, in <module>
    output = model.generate_from_batch(
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/allenai/Molmo-7B-D-0924/b42b79548195a798866e64213a83e5b989074e69/modeling_molmo.py", line 2213, in generate_from_batch
    out = super().generate(
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2048, in generate
    result = self._sample(
  File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 3008, in _sample
    outputs = self(**model_inputs, return_dict=True)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/allenai/Molmo-7B-D-0924/b42b79548195a798866e64213a83e5b989074e69/modeling_molmo.py", line 2107, in forward
    outputs = self.model.forward(
  File "/root/.cache/huggingface/modules/transformers_modules/allenai/Molmo-7B-D-0924/b42b79548195a798866e64213a83e5b989074e69/modeling_molmo.py", line 1869, in forward
    image_features, cls_embed = self.vision_backbone(images, image_masks)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/.cache/huggingface/modules/transformers_modules/allenai/Molmo-7B-D-0924/b42b79548195a798866e64213a83e5b989074e69/modeling_molmo.py", line 1378, in forward
    image_features, cls_embed = self.encode_image(images)
  File "/root/.cache/huggingface/modules/transformers_modules/allenai/Molmo-7B-D-0924/b42b79548195a798866e64213a83e5b989074e69/modeling_molmo.py", line 1346, in encode_image
    mask = ~torch.all(images.view(B * T, N, D) == -1, dim=(1, 2), keepdim=True)
TypeError: all() received an invalid combination of arguments - got (Tensor, keepdim=bool, dim=tuple), but expected one of:
 * (Tensor input, *, Tensor out)
      didn't match because some of the keywords were incorrect: keepdim, dim
 * (Tensor input, int dim, bool keepdim, *, Tensor out)
 * (Tensor input, name dim, bool keepdim, *, Tensor out)