-
Notifications
You must be signed in to change notification settings - Fork 21
Support Mistral-3.1-24B #220
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
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.
Pull Request Overview
This PR adds support for the Mistral-3.1-24B model by enabling image handling and reusing the pixtral script. Key changes include updating dependency specifications in setup.py, modifying model training and state dict loading logic, and extending image processing and encoder modules with new parameters and patch merging functionality.
Reviewed Changes
Copilot reviewed 8 out of 9 changed files in this pull request and generated 2 comments.
Show a summary per file
File | Description |
---|---|
setup.py | Added dependency for pydantic version constraint |
eole/models/model.py | Updated training logic and state dict loading behavior |
eole/inputters/text_corpus.py | Introduced image_patch_size parameters in corpus processing |
eole/inputters/dynamic_iterator.py | Added image_patch_size support in iterator configuration |
eole/encoders/vision.py | Added PatchMerger and updated VisionLanguageAdapter to incorporate patches |
eole/config/run.py | Removed batch_size assertion for vision models |
eole/config/models.py | Added new fields for adapter bias and spatial merge configuration |
Files not reviewed (1)
- docs/source/Config/models.rst: Language not supported
Now works with images, same script as pixtral.