Update app.py

app.py

@@ -1,4 +1,5 @@
 import os
+import tempfile
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from huggingface_hub import login
@@ -7,10 +8,9 @@ from dotenv import load_dotenv
 # Load environment variables
 load_dotenv()
 
-# Explicitly set a writable cache directory
-writable_cache_dir = "/tmp/huggingface_cache"
+# Create a temporary cache directory
+writable_cache_dir = tempfile.mkdtemp()
 os.environ["TRANSFORMERS_CACHE"] = writable_cache_dir
-os.makedirs(writable_cache_dir, exist_ok=True)
 
 # Retrieve the Hugging Face API token from environment variables
 api_token = os.getenv("ttt")
@@ -20,7 +20,7 @@ if not api_token:
 
 # Log in to Hugging Face with the token
 try:
-    login(api_token)  # Authenticate using the Hugging Face token
+    login(api_token)
     print("Successfully logged in to Hugging Face.")
 except Exception as e:
     print(f"Failed to log in to Hugging Face: {e}")
@@ -39,8 +39,8 @@ try:
     # Load the model with 4-bit quantization
     model = AutoModelForCausalLM.from_pretrained(
         model_name,
-        load_in_4bit=True,  # Enable 4-bit quantization
-        device_map="auto"   # Automatically map to GPU or CPU
+        load_in_4bit=True,
+        device_map="auto"
     )
 
     # Input text to the model
@@ -59,4 +59,4 @@ try:
     print("Response:", response)
 
 except Exception as e:
-    print(f"An error occurred: {e}")
+    print(f"An error occurred: {e}")