Update app.py

app.py

@@ -21,7 +21,8 @@ class StopOnTokens(StoppingCriteria):
         return False
 
 # Load the LLaMA model and tokenizer
-model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
+# model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
+model_id = 'mistralai/Mistral-7B-Instruct-v0.3'
 device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
 
 # Set quantization configuration