Update app.py

app.py

@@ -91,7 +91,7 @@ async def evaluate(
     max_new_tokens=128,
     seed=None,
     do_sample=True,
-    **kwargs,
+    # **kwargs,
 ):
     prompt = generate_prompt(input)
     inputs = tokenizer(prompt, return_tensors="pt")
@@ -101,7 +101,7 @@ async def evaluate(
         top_p=top_p,
         top_k=top_k,
         num_beams=num_beams,
-        **kwargs,
+        # **kwargs,
     )
     with torch.no_grad():
         generation_output = model.generate(