Fix bug in ggml_alibi #143
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
|
how does this relate to the discussion here #131 (comment) ? |
|
replit implementation seems to be fixed after this change |
|
Merging this based on the positive feedback |
|
Thank you @yangyaofei for this fix! I used the old ALiBi in another model and suffered a lot from it. |
|
@wangkuiyi you are welcome 😁 |
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Outdated suggestions cannot be applied.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.
According to NouamaneTazi/bloomz.cpp#27, I found there is a wrong implementation in
ggml_alibi.Now,
ggml_alibiwill get same result compare to thebuild_alibi_tensorintransformers.models.bloom.modeling_bloom