llm download

question_paper.py

@@ -19,7 +19,7 @@ app = FastAPI()
 @app.get("/")
 def llama():
     llm = Llama(
-      model_path="./models/7B/llama-model.gguf",
+      model_path="./Llama-2-7b-chat-hf-GGUF-Q4_K_M.gguf",
       # n_gpu_layers=-1, # Uncomment to use GPU acceleration
       # seed=1337, # Uncomment to set a specific seed
       # n_ctx=2048, # Uncomment to increase the context window