Update app.py

app.py

@@ -17,7 +17,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "gmonsoon/StockSeaLLMs-7B-v1"
+model_id = "gmonsoon/SahabatAI-Theta-15B-v1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -57,7 +57,6 @@ def generate(
         temperature=temperature,
         num_beams=1,
         repetition_penalty=repetition_penalty,
-        eos_token_id=tokenizer.eos_token_id,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()