royleibov

/

Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed

like 4

Hello, Thanks for uploading the model, I tried to use in my space https://huggingface.co/spaces/Wuyouz/English-Writing-Teacher/blob/main/app.py, but got an error:

Traceback (most recent call last):
  File "/home/user/app/app.py", line 13, in <module>
    model = AutoModelForPreTraining.from_pretrained("royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed")
  File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
  File "/usr/local/lib/python3.10/site-packages/zipnn/zipnn.py", line 1246, in custom_from_pretrained
    return original_from_pretrained.__func__(
  File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4238, in from_pretrained
    ) = cls._load_pretrained_model(
  File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4719, in _load_pretrained_model
    state_dict = load_state_dict(
TypeError: zipnn_hf.<locals>.custom_load_state_dict() got an unexpected keyword argument 'map_location'

Does it mean it supports GPU instances only?