-
Notifications
You must be signed in to change notification settings - Fork 12.2k
llama : fix embeddings #5796
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
llama : fix embeddings #5796
Changes from 1 commit
Commits
Show all changes
9 commits
Select commit
Hold shift + click to select a range
d034784
llama : fix embeddings
ggerganov eb42596
llama : do not use KV cache for non-causal models
ggerganov 9bbeb0f
embeddings : fix llama_batch_init arg
ggerganov e66da35
llama : add pooling switch
ggerganov 79e4eed
llama : distinguish token vs sequence embeddings
ggerganov fc9af15
llama : assert pooling tensor
ggerganov c23c554
llama : simplify causal mask condition
ggerganov 1af2d06
llama : assert input batch with pooling enabled
ggerganov 7cafaa4
readme : update API changes list
ggerganov File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
llama : add pooling switch
- Loading branch information
commit e66da356a41530137161d20feb224c76f5bc13ec
There are no files selected for viewing
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
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We should have the
LLAMA_POOLING_TYPE_MEAN
case join theLLAMA_POOLING_TYPE_CLS
case due to the output order of the averaging matrix.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes. I keep getting confused with the sequence-based instead of token-based embedding extraction.
Will try to modify the API to make things more clear
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Cool, this change fixes the NaNs from embedding.cpp, and results in the MSE of nomic-embed-text-v1.f16.gguf actually being lower than before (4.71e-10 vs 5.62e-10). Also fp32 is down from 9.34e-11 to 1.18e-14.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is likely due to no longer going through the KV cache.
Do you have any performance benchmarks to see if this change improved the speed?