fix(transformers): adds support for non-default head_dim in llama#3593
Closed
suniastar wants to merge 1 commit into
Closed
fix(transformers): adds support for non-default head_dim in llama#3593suniastar wants to merge 1 commit into
suniastar wants to merge 1 commit into
Conversation
suniastar
force-pushed
the
feat/llama-non-standard-head-dim
branch
from
f42d676 to
3d371fc
Compare
suniastar
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds support for non-standard/non-fallback
head_dimvalues.on huggingface head_dim is defined as
This PR adds support for the optional values as well as its gguf metadata counterparts
for the quantized llama model.
As my goal was to get MN Violet Lotus running with candle I was only able to test the quantized implemention due to lack of (V)RAM.