Update app.py

app.py

@@ -20,7 +20,7 @@ def inference(input_text):
     return {"output": res, "latency": f"{end_time - start_time:.2f} seconds"}
 
 # Initialize the tokenizer and model
-model_id = "NexaAIDev/android_API_10k_data"
+model_id = "NexaAIDev/Octopus-v2"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = GemmaForCausalLM.from_pretrained(
     model_id, torch_dtype=torch.bfloat16, device_map="auto"