Update modeling file

modeling_llava.py

@@ -1148,71 +1148,6 @@ class PhiForCausalLM(PhiPreTrainedModel):
             attentions=outputs.attentions,
         )
 
-    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.prepare_inputs_for_generation
-    def prepare_inputs_for_generation(
-        self,
-        input_ids,
-        past_key_values=None,
-        attention_mask=None,
-        inputs_embeds=None,
-        **kwargs,
-    ):
-        if past_key_values is not None:
-            if isinstance(past_key_values, Cache):
-                cache_length = past_key_values.get_seq_length()
-                past_length = past_key_values.seen_tokens
-                max_cache_length = past_key_values.get_max_length()
-            else:
-                cache_length = past_length = past_key_values[0][0].shape[2]
-                max_cache_length = None
-
-            # Keep only the unprocessed tokens:
-            # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
-            # input)
-            if (
-                attention_mask is not None
-                and attention_mask.shape[1] > input_ids.shape[1]
-            ):
-                input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]
-            # 2 - If the past_length is smaller than input_ids', then input_ids holds all input tokens. We can discard
-            # input_ids based on the past_length.
-            elif past_length < input_ids.shape[1]:
-                input_ids = input_ids[:, past_length:]
-            # 3 - Otherwise (past_length >= input_ids.shape[1]), let's assume input_ids only has unprocessed tokens.
-
-            # If we are about to go beyond the maximum cache length, we need to crop the input attention mask.
-            if (
-                max_cache_length is not None
-                and attention_mask is not None
-                and cache_length + input_ids.shape[1] > max_cache_length
-            ):
-                attention_mask = attention_mask[:, -max_cache_length:]
-
-        position_ids = kwargs.get("position_ids", None)
-        if attention_mask is not None and position_ids is None:
-            # create position_ids on the fly for batch generation
-            position_ids = attention_mask.long().cumsum(-1) - 1
-            position_ids.masked_fill_(attention_mask == 0, 1)
-            if past_key_values:
-                position_ids = position_ids[:, -input_ids.shape[1] :]
-
-        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
-        if inputs_embeds is not None and past_key_values is None:
-            model_inputs = {"inputs_embeds": inputs_embeds}
-        else:
-            model_inputs = {"input_ids": input_ids}
-
-        model_inputs.update(
-            {
-                "position_ids": position_ids,
-                "past_key_values": past_key_values,
-                "use_cache": kwargs.get("use_cache"),
-                "attention_mask": attention_mask,
-            }
-        )
-        return model_inputs
-
     @staticmethod
     # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM._reorder_cache
     def _reorder_cache(past_key_values, beam_idx):
@@ -1723,6 +1658,38 @@ class LlavaForCausalLM(LlavaPreTrainedModel):
                     attention_mask,
                     position_ids,
                 )
+            else:
+                # In case input_ids.shape[1] == 1 & pixel_values==None & past_key_values != None, we are in the case of
+                # generation with cache
+                if past_key_values is not None and image_features is not None and input_ids.shape[1] == 1:
+                    # Retrieve the first layer to inspect the logits and mask out the hidden states
+                    # that are set to 0
+                    first_layer_past_key_value = past_key_values[0][0][:, :, :, 0]
+
+                    # Sum all dimensions of head_dim (-2) to avoid random errors such as: https://github.com/huggingface/transformers/pull/28032#issuecomment-1863691941
+                    batch_index, non_attended_tokens = torch.where(first_layer_past_key_value.float().sum(-2) == 0)
+
+                    # Get the target length
+                    target_seqlen = first_layer_past_key_value.shape[-1] + 1
+
+                    extended_attention_mask = torch.ones(
+                        (attention_mask.shape[0], target_seqlen - attention_mask.shape[1]),
+                        dtype=attention_mask.dtype,
+                        device=attention_mask.device,
+                    )
+
+                    # Filter out only the tokens that can be un-attended, this can happen
+                    # if one uses Llava + Fused modules where the cache on the
+                    # first iteration is already big enough, or if one passes custom cache
+                    valid_indices = non_attended_tokens < extended_attention_mask.size(-1)
+                    new_batch_index = batch_index[valid_indices]
+                    new_non_attended_tokens = non_attended_tokens[valid_indices]
+
+                    # Zero-out the places where we don't need to attend
+                    extended_attention_mask[new_batch_index, new_non_attended_tokens] = 0
+
+                    attention_mask = torch.cat((attention_mask, extended_attention_mask), dim=1)
+                    position_ids = torch.sum(attention_mask, dim=1).unsqueeze(-1) - 1
 
         outputs = self.language_model(
             input_ids=None,
@@ -1759,13 +1726,49 @@ class LlavaForCausalLM(LlavaPreTrainedModel):
         image_features=None,
         **kwargs,
     ):
-        res = self.language_model.prepare_inputs_for_generation(
-            input_ids, past_key_values, attention_mask, **kwargs
-        )
-        input_ids = res["input_ids"]
-        past_key_values = res["past_key_values"]
-        attention_mask = res["attention_mask"]
+        if past_key_values is not None:
+            if isinstance(past_key_values, Cache):
+                cache_length = past_key_values.get_seq_length()
+                past_length = past_key_values.seen_tokens
+                max_cache_length = past_key_values.get_max_length()
+            else:
+                cache_length = past_length = past_key_values[0][0].shape[2]
+                max_cache_length = None
+
+            # Keep only the unprocessed tokens:
+            # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
+            # input)
+            if (
+                attention_mask is not None
+                and attention_mask.shape[1] > input_ids.shape[1]
+            ):
+                input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]
+            # 2 - If the past_length is smaller than input_ids', then input_ids holds all input tokens. We can discard
+            # input_ids based on the past_length.
+            elif past_length < input_ids.shape[1]+image_features.shape[1]-1:
+                past_length -= image_features.shape[1]-1
+                input_ids = input_ids[:, past_length:]
+                attention_mask = attention_mask[:, past_length:]
+            # 3 - Otherwise (past_length >= input_ids.shape[1]), let's assume input_ids only has unprocessed tokens.
+
+            # If we are about to go beyond the maximum cache length, we need to crop the input attention mask.
+            if (
+                max_cache_length is not None
+                and attention_mask is not None
+                and cache_length + input_ids.shape[1] > max_cache_length
+            ):
+                attention_mask = attention_mask[:, -max_cache_length:]
 
+        position_ids = kwargs.get("position_ids", None)
+        if attention_mask is not None and position_ids is None:
+            # create position_ids on the fly for batch generation
+            position_ids = attention_mask.long().cumsum(-1) - 1
+            position_ids.masked_fill_(attention_mask == 0, 1)
+            if past_key_values:
+                position_ids = position_ids[:, -input_ids.shape[1] :]
+
+        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
         if inputs_embeds is not None and past_key_values is None:
             model_inputs = {"inputs_embeds": inputs_embeds}
         else:
@@ -1773,6 +1776,7 @@ class LlavaForCausalLM(LlavaPreTrainedModel):
 
         model_inputs.update(
             {
+                "position_ids": position_ids,
                 "past_key_values": past_key_values,
                 "use_cache": kwargs.get("use_cache"),
                 "attention_mask": attention_mask,