moving monkeypatch

src/axolotl/monkeypatch/attention/differential.py

@@ -3,7 +3,7 @@
 from transformers import PreTrainedModel
 from transformers.models.llama.modeling_llama import LLAMA_ATTENTION_CLASSES
 
-from .multihead_diffattn import (
+from axolotl.integrations.diff_transformer.multihead_diffattn import (
     LlamaDifferentialAttention,
     LlamaDifferentialSdpaAttention,
 )

src/axolotl/utils/models.py

@@ -445,7 +445,7 @@ class ModelLoader:
             patch_mistral_cross_entropy()
 
         if self.cfg.diff_attention:
-            from axolotl.integrations.diff_transformer.patches import (
+            from axolotl.monkeypatch.attention.differential import (
                 patch_llama_attention_classes,
             )