Refactor/fix Cohere2 #35594
Merged
Refactor/fix Cohere2 #35594
Conversation
This file contains 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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
cc @ArthurZucker, and @alexrs-cohere if you want to have a look! |
ArthurZucker
approved these changes
Jan 9, 2025
| @@ -181,117 +175,29 @@ def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1): | |||
|
|
|||
|
|
|||
| def eager_attention_forward( | |||
| config: Cohere2Config, | |||
| module: nn.Module, | |||
| dropout: float = 0.0, | ||
| **kwargs, | ||
| ): | ||
| key_states = repeat_kv(key, module.num_key_value_groups) |
There was a problem hiding this comment.
Oh indeed, good point! More code cut 🤗
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Outdated suggestions cannot be applied.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.
What does this PR do?
Refactor Cohere2 to meet recent standards, and fix #35547 at the same time