Update app.py

LLM_MODEL = "meta-llama/Llama-3.1-8B-Instruct"

app.py

@@ -13,7 +13,8 @@ from huggingface_hub import InferenceClient
 HF_TOKEN = os.getenv("HF_TOKEN", None)
 
 # Free model compatible with new HF API
-LLM_MODEL = "meta-llama/Llama-3.2-1B-Instruct"
+#LLM_MODEL = "meta-llama/Llama-3.2-1B-Instruct"
+LLM_MODEL = "meta-llama/Llama-3.1-8B-Instruct"
 
 # Local embedding model
 EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"