fix: inputs problem

app.py

@@ -26,16 +26,18 @@ def inference(prompt: str, max_tokens: int = 256) -> str:
         tokenize = False,
         add_generation_prompt = True, # Must add for generation
     )
+    inputs = tokenizer(text, return_tensors="pt").to("cuda")
     
     outputs = model.generate(
-        **tokenizer(text, return_tensors = "pt").to("cuda"),
-        max_new_tokens = 100, # Increase for longer outputs!
-        temperature = 0.7, top_p = 0.8, top_k = 20, # For non thinking
-        streamer = TextStreamer(tokenizer, skip_prompt = True),
+        **inputs,
+        max_new_tokens=max_tokens,
+        temperature=0.7,
+        top_p=0.8,
+        top_k=20,
     )
 
     response = tokenizer.decode(
-        outputs[0][inputs["input_ids"].shape[1]:],  # slice from end of input
+        outputs[0][inputs["input_ids"].shape[1]:],
         skip_special_tokens=True
     )
     return response