Skip to content

Conversation

@bryce13950
Copy link
Collaborator

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # (issue)

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Screenshots

Please attach before and after screenshots of the change if applicable.

Checklist:

  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • I have not rewritten tests relating to key interfaces which would affect backward compatibility

thisnick and others added 3 commits February 19, 2025 21:58
* moved setup python

* added PR action

* temporarily hardcoded version number

* moved poetry

* Revert "temporarily hardcoded version number"

This reverts commit 23a7be8.

* Revert "added PR action"

This reverts commit b08c241.

* Add Mistral Small model and update Mistral rotary dimension

- Added "mistralai/Mistral-Small-24B-Base-2501" to OFFICIAL_MODEL_NAMES
- Updated rotary dimension from 32 to 128 for Mistral models

* Update pyproject.toml dependencies and configuration

- Relaxed transformers version constraint for Python 3.9+
- Added typeguard dependency
- Reordered and cleaned up mypy configuration exclude rules

* Minor pyproject.toml formatting revert pyptojct.toml

* update model count

* Add Mistral Small 24B model to Colab compatibility demo

---------

Co-authored-by: Bryce Meyer <[email protected]>
* Bert masked language modelling refactor

* Implement Next sentence prediction for BERT

* Implement tokenization

* Add more bert models

* Allowing return type predictions to directly return model predictions instead of logits

* Fix unrelated typos

* Reflect changes in BERT notebook

* Adjust colab_compatibility

* Add test cases

* Type hinting

* Format

* Remove embeddings as input to forward function

* Create own class for NextSentencePrediction

* Inject HookedEncoder as dependency and add tests accordingly

* updated total line

* regenerated contents of cell

---------

Co-authored-by: Fabian Degen <[email protected]>
Co-authored-by: Bryce Meyer <[email protected]>
* fixed bert indenting

* fixed indentation

* fixed spacing
@bryce13950 bryce13950 merged commit e65fafb into main Feb 20, 2025
26 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants