fixes

app.py

@@ -4,15 +4,11 @@ import time
 import json
 import requests
 import threading
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, TextIteratorStreamer
-from peft import PeftModel
-
-print("CUDA available:", torch.cuda.is_available())
-if torch.cuda.is_available():
-    print(f"CUDA device count: {torch.cuda.device_count()}")
-    print(f"CUDA device: {torch.cuda.get_device_name(0)}")
-    print(f"CUDA memory: {torch.cuda.get_device_properties(0).total_memory / 1e9:.2f} GB")
 
+"""
+This app uses the Hugging Face Inference API to generate responses from the
+Trinoid/Data_Management_Mistral model.
+"""
 # Get token from environment
 HF_TOKEN = os.environ.get("HF_TOKEN")
 print(f"HF_TOKEN is {'available' if HF_TOKEN else 'not available'}")