transformers
Support `num_attention_heads` != `num_key_value_heads` in Flax Llama Implementation
#29557
Merged

Support `num_attention_heads` != `num_key_value_heads` in Flax Llama Implementation #29557

ArthurZucker merged 5 commits into huggingface:main from bminixhofer:master
bminixhofer
bminixhofer fix tinyllama flax modelling
d6369445
bminixhofer rename vars to minimize changes
05a3b878
bminixhofer move
0a69815c
bminixhofer formatting
d266d0e7
bminixhofer remove unused var
0c2345fe
bminixhofer
ArthurZucker
ArthurZucker approved these changes on 2024-03-26
HuggingFaceDocBuilderDev
bminixhofer
ArthurZucker
ArthurZucker ArthurZucker merged 8e08acad into main 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone