Update app.py

app.py

@@ -13,7 +13,7 @@ from transformers import TextIteratorStreamer
 
 # Load the base model and tokenizer
 base_model = AutoModelForCausalLM.from_pretrained(
-    'meta-llama/Llama-2-7b-chat-hf',
+    'NousResearch/Llama-2-7b-chat-hf',
     trust_remote_code=True,
     device_map="auto",
     torch_dtype=torch.float16,