run

question_paper.py

@@ -1,7 +1,6 @@
-import transformers
-import torch
-
-from fastapi import FastAPI, Response
+from fastapi import FastAPI
+from fastapi.encoders import jsonable_encoder
+from fastapi.responses import JSONResponse
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -32,7 +31,8 @@ def llama():
     # tresponse = TOKENIZER.decode(tokens[0], skip_special_tokens=False)
     # print(tresponse)
     response_message = {"message": "hello world"}
-    return Response(content=response_message, media_type="application/json")
+    json_response = jsonable_encoder(response_message)
+    return JSONResponse(content=json_response)
  
 # @app.on_event("startup")
 # def init_model():