Update app.py

app.py

@@ -2,12 +2,15 @@ import os
 import gradio as gr
 import torch
 import spaces
+from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer if a GPU is available
 if torch.cuda.is_available():
-    model_id = "yilunzhao/olmo-finetuned"
+    model_id = "allenai/OLMo-7B-Instruct"
+    adapters_name = "yilunzhao/olmo-finetuned"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
+    model = PeftModel.from_pretrained(model, adapters_name)
     tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 else:
     raise EnvironmentError("CUDA device not available. Please run on a GPU-enabled environment.")