Update app.py

app.py

@@ -18,7 +18,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 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 = "meta-llama/Llama-3.1-8B"
+model_id = "meta-llama/Llama-3.2-1B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -26,6 +26,7 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.float16,
     load_in_8bit=True,
 )
+
 model.eval()
 @spaces.GPU(duration=90)
 def generate(
@@ -36,7 +37,7 @@ def generate(
     top_k: int = 50,
     repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
-    prompt = f"[INST] {message} [/INST]"
+    prompt = f"{message}"
     input_ids = tokenizer.encode(prompt, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]