Merge branch 'main' of https://huggingface.co/akhauriyash/Llama-3.2-3B-Butler into main

modeling_llama_butler.py

@@ -912,6 +912,7 @@ class LlamaAttentionExperimental(nn.Module):
         self.max_position_embeddings = config.max_position_embeddings
         self.rope_theta = config.rope_theta
         self.inference_mode = True
+        self.inference_mode = True
         self.producer = producer
         self.layer_idx = layer_idx
         self.token_sparse_method = None

pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4dfa822ca3de909a86b2e953a80c6a91ce388231b275cc27ad6907e269a2f0
+size 4990856976

pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba19c1b60c89c7006625d89cf0c9336a7cd21b1192595c2fc84425af979f546d
+size 4970557824

pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a8f099bb6c579af2b208c16345e0d6e38ecaf763c13ec02c42d1cf1bfe472f
+size 3020115584