Update app.py

app.py

@@ -184,8 +184,8 @@ def model_inference(input_dict, history):
         ).to("cuda")
         
         streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=False)
-        # generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024, temperature=0.1, top_p=0.95, top_k=50)
-        generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024, do_sample=False, num_beams=1)
+        generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024, temperature=0.1, top_p=0.95, top_k=50)
+        # generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024, do_sample=False, num_beams=1)
         thread = Thread(target=model.generate, kwargs=generation_kwargs)
         thread.start()