Qwen

/

Qwen2-VL-2B-Instruct

like 333

Follow

Qwen 7.25k

Following the doc tutorial, install transformers with latest git commit:

pip install git+https://github.com/huggingface/transformers

and the model loading step:

from transformers import Qwen2VLForConditionalGeneration
model = Qwen2VLForConditionalGeneration.from_pretrained(
    pretrained_model_name_or_path="Qwen/Qwen2-VL-2B-Instruct",
    torch_dtype="auto",
    device_map="auto",
)

raise errors:

  File "/home/xxx/xxx/qwen2.py", line 1, in <module>
    from transformers import Qwen2VLForConditionalGeneration
  File "<frozen importlib._bootstrap>", line 1039, in _handle_fromlist
  File "/home/xxx/xxx/.venv/lib/python3.8/site-packages/transformers/utils/import_utils.py", line 1657, in __getattr__
    value = getattr(module, name)
  File "/home/xxx/xxx/.venv/lib/python3.8/site-packages/transformers/utils/import_utils.py", line 1656, in __getattr__
    module = self._get_module(self._class_to_module[name])
  File "/home/xxx/xxx/.venv/lib/python3.8/site-packages/transformers/utils/import_utils.py", line 1668, in _get_module
    raise RuntimeError(
RuntimeError: Failed to import transformers.models.qwen2_vl.modeling_qwen2_vl because of the following error (look up to see its traceback):
Failed to import transformers.generation.utils because of the following error (look up to see its traceback):
issubclass() arg 1 must be a class

Is there a issue with latest transformer version(60226fd) for Qwen2-VL integration?