-
Notifications
You must be signed in to change notification settings - Fork 463
[v2] Refactor CoPali new interface #2844
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@@ -38,15 +41,42 @@ def __init__( | |||
|
|||
# Load model | |||
self.mdl = model_class.from_pretrained( | |||
model_name, revision=revision, device_map=self.device, **kwargs | |||
model_name, device_map=self.device, **kwargs |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
With revision there, I kept running into this error, which disappeared when I removed revision:
File "/opt/homebrew/anaconda3/envs/mteb/lib/python3.11/site-packages/transformers/modeling_utils.py", line 1100, in _get_resolved_checkpoint_files raise EnvironmentError( OSError: vidore/colpaligemma-3b-mix-448-base does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt or flax_model.msgpack.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't think that we want to remove revision here. Which model did you use?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I tested all 3. Could you see if you can run any of these successfully with revision?
mteb run -m vidore/colpali-v1.2 -t MNIST
Fixes #2771
If you add a model or a dataset, please add the corresponding checklist: