Update app.py

app.py

@@ -12,7 +12,7 @@ from transformers import pipeline, AutoTokenizer
 
 pipe = pipeline(
     "text-generation", 
-    model="meta-llama/Meta-Llama-3-8B", 
+    model="QuantFactory/Meta-Llama-3-8B-Instruct-GGUF", 
     model_kwargs={"torch_dtype": torch.bfloat16}, 
     device_map="auto"
 )