Update app.py

app.py

@@ -46,12 +46,13 @@ def correct_text2(text, genConfig):
     corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return corrected_text
 
-def respond(text, max_length, min_length, max_new_tokens, min_new_tokens, num_beams, temperature, top_p):
+def respond(text, max_length, min_length, max_new_tokens, min_new_tokens, num_beams, temperature: float, top_k, top_p: float):
     config = GenerationConfig(
         max_length=max_length,
         min_length=min_length,
         num_beams=num_beams,
         temperature=temperature,
+        top_k=top_k,
         top_p=top_p,
         early_stopping=True,
         do_sample=True
@@ -96,7 +97,9 @@ with gr.Blocks() as demo:
         min_tokens = gr.Slider(minimum=0, maximum=256, value=0, step=1, label="Min New Tokens")
         num_beams = gr.Slider(minimum=1, maximum=10, value=5, step=1, label="Num Beams")
         temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+        top_k = gr.Slider(minimum=0, maximum=200, value=50, step=1, label="Top-k")
         top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
+        
 
     
     submitBtn.click(respond, [prompt_box, max_length, min_length, max_tokens, min_tokens, num_beams, temperature, top_p], output_box)