tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

various improvemnents

Browse Source
This commit is contained in:
Dan Saunders
2024-12-13 15:17:52 -05:00
parent 7108ca72b4
commit 845dbede53
2 changed files with 2 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/axolotl/integrations/diff_transformer/multihead_diffattn.py
View File

@@ -292,8 +292,8 @@ class LlamaDifferentialSdpaAttention(LlamaDifferentialAttention):
'but specifying the manual implementation will be required from Transformers version v5.0.0 onwards. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.'
)
return super().forward(
hidden_states=hidden_states,
attention_mask=attention_mask,
hidden_states=hidden_states, # pylint: disable=duplicate-code
attention_mask=attention_mask, # pylint: disable=duplicate-code
position_ids=position_ids,
past_key_value=past_key_value,
output_attentions=output_attentions,