Release 2.16 #945
Merged
Release 2.16 #945
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* created a seperate list of models to test for public PRs * ran format
Co-authored-by: Bryce Meyer <[email protected]>
* Fix loading on specific device * format --------- Co-authored-by: Bryce Meyer <[email protected]>
* Implement Qwen3 qk normalization * Add QK norm to correct class * reuse module * format * alias * remove qk norm eps * updated notebook * reran notebook * fixed mypy issues in conversion * checked q norm and k norm value before use --------- Co-authored-by: fellows-safety <[email protected]> Co-authored-by: Bryce Meyer <[email protected]>
Co-authored-by: Bryce Meyer <[email protected]>
Only for Qwen Co-authored-by: Bryce Meyer <[email protected]>
* updated mypy * fixed mypy issues * restored neel nanda config * fixed typing * removed extra reference * restored model aliases * restored python 3.9 compatibility * removed irrelevant test * ran format * fixed import * restored python 3.9 items
* upated torch * fixed some mypy issues * fixed some mypy issues * fixed param passing * updated some dependencies * fixed test * ran format * ran format * fixed some mypy issues * fixed mypy issues * fixed mypy issues in HookedTransformer * fixed abstract attention mypy issues * fixed attention bug * fixed mypy issues * fixed potential name collision * asserted type * fixed param * ignored type check
* updated transformers * updated torch * updated mypy * updated mypy dependency * lowered ceiling of mypy * removed mypy ceiling * capped mypy * fixed some more mypy transformers incompatibilities * restored pythong 3.9 compat * fixed mypy errors * ran format * fixed mypy issues * fixed more mypy issues * fixed another mypy issue * fixed test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist: