fixing cache issue

app.py

@@ -1,17 +1,18 @@
+import os
 from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import uvicorn
 
-# Load model and tokenizer once at startup
+# Set writable cache directory
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/cache"
+
 MODEL_NAME = "16pramodh/t2s_model"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
 
-# Create FastAPI app
 app = FastAPI()
 
-# Request body format
 class QueryRequest(BaseModel):
     text: str
 
@@ -25,6 +26,5 @@ def predict(request: QueryRequest):
     except Exception as e:
         return {"error": str(e)}
 
-# For local testing
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)