Update app.py

app.py

@@ -22,7 +22,7 @@ For more details, please check [our post](https://huggingface.co/blog/llama32).
 access_token = os.getenv('HF_TOKEN')
 # Download the Base model
 #model_id = "./models/Llama-32-3B-Instruct"
-model_id = "princeton-nlp/gemma-2-9b-it-SimPO"
+model_id = "lmsys/vicuna-7b-v1.5"
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
@@ -32,7 +32,7 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 #model_id = "nltpt/Llama-3.2-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id,token=access_token)
 #tokenizer.padding_side = 'right'
-tokenizer.eos_token_id = 107
+#tokenizer.eos_token_id = 107
 tokenizer.pad_token = tokenizer.eos_token
 model = AutoModelForCausalLM.from_pretrained(
     model_id,