Update app.py

app.py

@@ -3,6 +3,10 @@ import json
 import random
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import os
+
+# Set the TRANSFORMERS_CACHE environment variable
+os.environ['TRANSFORMERS_CACHE'] = '/app/cache'
 
 app = Flask(__name__)