Update app.py

app.py

@@ -33,12 +33,6 @@ model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     load_in_4bit=True,
     trust_remote_code=True
 )
-model = model.cuda()
-
-# Load the model and tokenizer using transformers
-# model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-6B-200K", trust_remote_code=True)
-
-# model = BetterTransformer.transform(model)
 
 def run(message, chat_history, max_new_tokens=20000, temperature=1.5, top_p=0.9, top_k=900):
     prompt = get_prompt(message, chat_history)