Test llama architecture adapter#1311
Open
indrayani21 wants to merge 7 commits into
Open
Conversation
* Fix type of HookedTransformerConfig.device This is typed as `Optional[str]` but sometimes returns `torch.device`. Updated the code to just return the `str` instead of wrapping with a device. I'm not confident that every function which takes a device will always be passed a string, so I didn't change functions like warn_if_mps. Found while working on TransformerLensOrg#1219 * more cleanup * 3.0 CI Bugs (TransformerLensOrg#1261) * Fixing `utils` imports * skip gated notebooks on PR from forks * Updating notebooks * Ensure LLaMA only runs when HF_TOKEN is available --------- Co-authored-by: jlarson4 <jonahalarson@comcast.net>
TransformerLens 3.1.0
jlarson4
reviewed
May 18, 2026
Collaborator
jlarson4
left a comment
jlarson4
left a comment
There was a problem hiding this comment.
This PR is solid as well! Just one note on the rotary_emb assertion, and you'll need to clean up any formatting errors. Let me know if you have any questions @indrayani21
| ) | ||
|
|
||
| # Verify method exists and adapter remains usable | ||
| assert hasattr(attn_bridge, "set_rotary_emb") |
Collaborator
There was a problem hiding this comment.
This assertion cannot fail due to the way the attention bridge constructs LLaMA's rotary_emb. It would be more valuable to assert assert attn_bridge._rotary_emb is rotary_emb
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds focused unit tests for the Llama architecture adapter in
tests/unit/model_bridge/supported_architectures/test_llama_adapter.py.This PR adds validation for:
n_key_value_heads) supportThe tests were modeled after the existing CodeGen adapter test suite and adapted for Llama-specific behaviors such as:
Related to #1302
Type of change
Checklist:
-->