Update app.py

app.py

@@ -1,4 +1,4 @@
-import gradio as gr
+"""import gradio as gr
 import torch
 import time
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
@@ -79,7 +79,7 @@ def generate_response(message, temperature, max_new_tokens, top_p, task):
     print(f"Prompt: {prompt}")
     start_time = time.time()
     inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(input_ids=inputs, do_sample=True, max_new_tokens=max_new_tokens, use_cache=True, temperature=temperature, min_p=top_p, pad_token_id=tokenizer.eos_token_id)
+    outputs = model.generate(input_ids=inputs, max_new_tokens=max_new_tokens, use_cache=True, temperature=temperature, min_p=top_p, pad_token_id=tokenizer.eos_token_id)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     processed_response = response.split("RESPONSE :")[-1].strip()
     end_time = time.time()
@@ -111,4 +111,4 @@ with gr.Blocks(theme='1024m/1024m-1') as demo:
     send_btn.click(fn=generate_response, inputs=[input_text, temperature, max_new_tokens, top_p, task_dropdown], outputs=output_text)
     clear_btn.click(fn=lambda: ("", ""), inputs=None, outputs=[input_text, output_text])
 if __name__ == "__main__":
-    demo.queue().launch()"""
+    demo.queue().launch()