Update modeling_llama3.py

modeling_llama3.py

@@ -80,8 +80,6 @@ class Llama3ForCausalLM(Llama3PreTrainedModel, GenerationMixin):
         input_ids: Optional[torch.LongTensor] = None,
         audio_features: Optional[torch.FloatTensor] = None,
         attention_mask: Optional[torch.Tensor] = None,
-        cross_attention_mask: Optional[torch.Tensor] = None,
-        cross_attention_states: Optional[torch.Tensor] = None,
         position_ids: Optional[torch.LongTensor] = None,
         past_key_values: Optional[List[torch.FloatTensor]] = None,
         inputs_embeds: Optional[torch.FloatTensor] = None,
@@ -152,8 +150,6 @@ class Llama3ForCausalLM(Llama3PreTrainedModel, GenerationMixin):
             input_ids=None,
             attention_mask=attention_mask,
             position_ids=position_ids,
-            cross_attention_states=cross_attention_states,
-            cross_attention_mask=cross_attention_mask,
             full_text_row_masked_out_mask=None,
             past_key_values=past_key_values,
             use_cache=use_cache,
@@ -175,9 +171,6 @@ class Llama3ForCausalLM(Llama3PreTrainedModel, GenerationMixin):
         inputs_embeds=None,
         attention_mask=None,
         position_ids=None,
-        aspect_ratio_ids=None,
-        aspect_ratio_mask=None,
-        cross_attention_mask=None,
         past_key_values=None,
         use_cache=False,
         cache_position=None,
@@ -224,7 +217,6 @@ class Llama3ForCausalLM(Llama3PreTrainedModel, GenerationMixin):
                 "past_key_values": past_key_values,
                 "use_cache": use_cache,
                 "attention_mask": attention_mask,
-                "cross_attention_mask": cross_attention_mask,
             }
         )