Update app.py

app.py

@@ -6,10 +6,9 @@ from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Model Name from Hugging Face
 MODEL_NAME = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
 
-# Load the model & tokenizer from Hugging Face (automatically uses CPU)
+# Load the model & tokenizer from Hugging Face
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16)
 
@@ -18,7 +17,6 @@ HEADERS = {"User-Agent": "Mozilla/5.0"}
 MAX_CASE_TEXT_LENGTH = 9500
 MAX_CONCURRENT_REQUESTS = 100
 
-# Threading for faster execution
 executor = ThreadPoolExecutor(max_workers=10)
 semaphore = asyncio.Semaphore(MAX_CONCURRENT_REQUESTS)