Update app.py

app.py

@@ -1,7 +1,7 @@
 import fastapi
 from fastapi.responses import JSONResponse
 from time import time
-from fastapi.middleware.cors import CORSMiddleware
+#from fastapi.middleware.cors import CORSMiddleware
 #MODEL_PATH = "./qwen1_5-0_5b-chat-q4_0.gguf" #"./qwen1_5-0_5b-chat-q4_0.gguf"
 import logging
 import llama_cpp
@@ -25,7 +25,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
     verbose=False,
      n_ctx=1024,
      n_gpu_layers=0,
-    #chat_format="llama-2"
+    chat_format="llama-2"
 )
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
@@ -37,7 +37,7 @@ llm_generate = llama_cpp.Llama.from_pretrained(
     mirostat_mode=2,
     mirostat_tau=4.0,
     mirostat_eta=1.1
-    #chat_format="llama-2"
+    chat_format="llama-2"
 )
 # Logger setup
 logging.basicConfig(level=logging.INFO)
@@ -83,7 +83,7 @@ async def chat(gen:GenModel):
         et = time()
         output["time"] = et - st
         messages.append({'role': "assistant", "content": output['choices'][0]['message']['content']})
-        print(messages)
+        #print(messages)
         return output
     except Exception as e:
         logger.error(f"Error in /complete endpoint: {e}")
@@ -131,5 +131,4 @@ async def generate(gen:GenModel):
 
 if __name__ == "__main__":
     import uvicorn
-
     uvicorn.run(app, host="0.0.0.0", port=7860)