Update app.py

app.py

@@ -8,22 +8,21 @@ MODEL_ID = "sakthi54321/power_NLP"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
     device_map="auto"
 )
 
+# Build pipeline (❌ no device arg here!)
 generator = pipeline(
     "text-generation",
     model=model,
-    tokenizer=tokenizer,
-    device=0 if torch.cuda.is_available() else -1
+    tokenizer=tokenizer
 )
 
 # Chat function
 def chat_fn(message, history):
-    prompt = message
     outputs = generator(
-        prompt,
+        message,
         max_new_tokens=200,
         temperature=0.7,
         top_p=0.9,