Update app.py

app.py

@@ -5,16 +5,16 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 os.environ["HF_HOME"] = "/data/hf_cache"
 
-tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-120b")
-model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-120b", device_map="auto", offload_folder="/data/offload")
+tokenizer = AutoTokenizer.from_pretrained("/data/model")
+model = AutoModelForCausalLM.from_pretrained("/data/model", device_map="auto", offload_folder="/tmp/offload")
 
 def get_stats():
     process = psutil.Process(os.getpid())
     ram = process.memory_info().rss / 1024 ** 3
     disk_tmp = psutil.disk_usage('/tmp').used / 1024 ** 3
-    disk_app = psutil.disk_usage('/').used / 1024 ** 3
+    disk_data = psutil.disk_usage('/data').used / 1024 ** 3
     cpu = psutil.cpu_percent(interval=1)
-    return f"RAM: {ram:.2f} GB | /tmp: {disk_tmp:.2f} GB | Disk: {disk_app:.2f} GB | CPU: {cpu:.1f}%"
+    return f"RAM: {ram:.2f} GB | /tmp: {disk_tmp:.2f} GB | /data: {disk_data:.2f} GB | CPU: {cpu:.1f}%"
 
 def chat(message, history):
     messages = []