push

model_manager.py

@@ -138,7 +138,7 @@ def generate_chat_response(prompt: str, max_length: int = 512, temperature: floa
                         raise
         
         generated_ids_trimmed = [
-            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, outputs)
+            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs['input_ids'], outputs)
         ]
         generated_text = style_processor.batch_decode(
             generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
@@ -228,7 +228,7 @@ async def generate_chat_response_streaming(prompt: str, max_length: int = 512, t
                         raise
         
         generated_ids_trimmed = [
-            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, outputs)
+            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs['input_ids'], outputs)
         ]
         generated_text = style_processor.batch_decode(
             generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False