Update modeling_quiet.py

modeling_quiet.py

@@ -1891,12 +1891,16 @@ class QuietForCausalLM(QuietPreTrainedModel, GenerationMixin):
         torch.cuda.empty_cache()
         
 
-        return CausalLMOutputWithPast(
-            loss=loss if loss is not None else None,
-            logits=(rm_logits if self.n_ahead > 1 else logits) if not self.output_logits_at_the_end else logits,
-            past_key_values=outputs.past_key_values,
-            hidden_states=outputs.hidden_states,
-            attentions=outputs.attentions,
+        return self.infer(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
         )
         
 
@@ -1904,59 +1908,18 @@ class QuietForCausalLM(QuietPreTrainedModel, GenerationMixin):
     def prepare_inputs_for_generation(
         self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs
     ):
-        # Omit tokens covered by past_key_values
-        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 inputs_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
+        if attention_mask is None:
+            attention_mask = input_ids.new_ones(input_ids.shape)
+
+        if past_key_values:
+            input_ids = input_ids[:, -1:]
+
+        return {
+            "input_ids": input_ids,
+            "attention_mask": attention_mask,
+            "past_key_values": past_key_values,
+            "inputs_embeds": inputs_embeds,
+        }
 
     @staticmethod
     def _reorder_cache(past_key_values, beam_idx):