Trying different Llama model

app.py

@@ -29,7 +29,8 @@ import transformers
 from accelerate import disk_offload
 
 # Model used
-model_id = 'meta-llama/Llama-2-7b-chat-hf'
+# model_id = 'meta-llama/Llama-2-7b-chat-hf'
+model_id = 'NousResearch/Llama-2-7b-chat-hf'
 
 # Detects available device (GPU or CPU)
 device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'