[Draft] Split qkv_proj
into q_proj
, k_proj
and v_proj
#90
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Outdated suggestions cannot be applied.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.
For models that stack the query, key, value projections in the attention layer, this PR splits the
qkv_proj
intoq_proj
,k_proj
, andv_proj
to allow for individual patching of the layers withLoRA
.This remove the need for
phi_2_align_heads
and replaces it withsplit_qkv
in theLoRAConfig
class.