Support `num_attention_heads` != `num_key_value_heads` in Flax Llama Implementation #29557
fix tinyllama flax modelling
d6369445
rename vars to minimize changes
05a3b878
move
0a69815c
formatting
d266d0e7
remove unused var
0c2345fe
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub