Use head_dim if in config for RoPE #32495
Merged
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
ArthurZucker
reviewed
Aug 7, 2024
There was a problem hiding this comment.
LGTM that looks like a regression (for llama at least) cc @gante !
5 tasks
|
@gante could you please take a look at this PR ? |
|
Hi @ArthurZucker @gante , may I ask if there is any update on this ? |
| @@ -58,7 +58,8 @@ def _compute_default_rope_parameters( | |||
| elif config is not None: | |||
| base = config.rope_theta | |||
| partial_rotary_factor = config.partial_rotary_factor if hasattr(config, "partial_rotary_factor") else 1.0 | |||
| dim = int((config.hidden_size // config.num_attention_heads) * partial_rotary_factor) | |||
| head_dim = config.head_dim if hasattr(config, "head_dim") else config.hidden_size // config.num_attention_heads | |||
There was a problem hiding this comment.
Suggested change
| head_dim = config.head_dim if hasattr(config, "head_dim") else config.hidden_size // config.num_attention_heads | |
| head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads) |
There was a problem hiding this comment.
thanks for catching this! just fixed!
|
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. |
ArthurZucker
approved these changes
Aug 16, 2024
ArthurZucker
pushed a commit
that referenced
this pull request
Aug 16, 2024
* use head_dim if in config for RoPE * typo * simplify with getattr
ArthurZucker
pushed a commit
that referenced
this pull request
Aug 20, 2024
* use head_dim if in config for RoPE * typo * simplify with getattr
ArthurZucker
pushed a commit
that referenced
this pull request
Aug 20, 2024
* use head_dim if in config for RoPE * typo * simplify with getattr
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?
Fixes issue that when head_dim * num_attention_heads != hidden_size, the RoPE is not initialized correctly
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.