question

question_paper.py

@@ -30,11 +30,9 @@ def llama(input):
 
     # tresponse = TOKENIZER.decode(tokens[0], skip_special_tokens=False)
     # print(tresponse)
-    outputs = generator(input, max_length=100)
-    text = ""
-    for o in outputs:
-        text = text + ' ' + o["generated_text"]
-    response_message = {"message": text}
+    output = generator(input, max_length=100)
+    
+    response_message = {"message": output["generated_text"]}
     json_response = jsonable_encoder(response_message)
     return JSONResponse(content=json_response)