Update app.py

app.py

@@ -24,7 +24,7 @@ examples = [
 ]
 
 model_name = "berkeley-nest/Starling-RM-7B-alpha"
-base_model = "meta-llama/Llama-2-7b-chat-hf"
+# base_model = "meta-llama/Llama-2-7b-chat-hf"
 
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -34,7 +34,7 @@ top_p=0.92
 repetition_penalty=1.7
 
 
-tokenizer = transformers.AutoTokenizer.from_pretrained(base_model)
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     device_map="auto",
     torch_dtype=torch.bfloat16,