Update app/llm.py

app/llm.py

@@ -31,9 +31,9 @@ class ChatModel(BaseModel):
 llm_chat = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
-    #tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat-GGUF"),
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat"),
     verbose=False,
-     n_ctx=256,
+     n_ctx=128,
      n_gpu_layers=0,
     #chat_format="llama-2"
 )