Update app.py

app.py

@@ -22,7 +22,8 @@ class StopOnTokens(StoppingCriteria):
 
 # Load the LLaMA model and tokenizer
 # model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
-model_id= "meta-llama/Llama-2-7b-chat-hf"
+# model_id= "meta-llama/Llama-2-7b-chat-hf"
+model_id="mistralai/Mistral-7B-Instruct-v0.2"
 device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
 
 # Set quantization configuration