Upload HymbaForCausalLM

README.md

@@ -1,9 +1,9 @@
 ---
 library_name: transformers
-pipeline_tag: text-generation
 license: other
 license_name: nvidia-open-model-license
 license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
+pipeline_tag: text-generation
 ---
 
 # Hymba-1.5B-Instruct 

modeling_hymba.py

@@ -1233,7 +1233,7 @@ class HymbaFlexAttention(HymbaFlashAttention2):
 
         self.attn_mask = or_masks(attn_mask, register_mask)
 
-        self.block_mask = create_block_mask(self.attn_mask, B=None, H=None, Q_LEN=qk_length, KV_LEN=qk_length, _compile=True)
+        self.block_mask = create_block_mask(self.attn_mask, B=None, H=None, Q_LEN=qk_length, KV_LEN=qk_length)
 
         self.flex_attention = torch.compile(flex_attention)