Update app.py

app.py

@@ -12,7 +12,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available() or os.getenv("ZERO_GPU_SUPPORT", False):
-    model_id = "infly/OpenCoder-1.5B-Instruct"
+    model_id = "infly/OpenCoder-8B-Instruct"
     model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16)
     tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 else: