Update app.py

app.py

@@ -22,7 +22,7 @@ vectorstore = FAISS.load_local(
 retriever = vectorstore.as_retriever()
 
 # ==========================================
-# 2. Load Model & Tokenizer in 16-bit (ZeroGPU Fix)
+# 2. Load Model & Tokenizer in 16-bit
 # ==========================================
 print("Loading Model...")
 model_id = "anirudh248/llama3-upf-generator"
@@ -31,8 +31,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto"
+    torch_dtype=torch.bfloat16
 )
 model.generation_config.pad_token_id = tokenizer.eos_token_id