Update app.py

app.py

@@ -102,7 +102,7 @@ def model_inference(input_dict, history):
         ).to("cuda")
         # Set up streaming generation.
         streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
-        generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=256, min_p=0.01, no_repeat_ngram_size=1, temperature=4, num_beams=5, repetition_penalty=1.5)
+        generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=256, no_repeat_ngram_size=20, temperature=2, num_beams=5, repetition_penalty=1.5)
         thread = Thread(target=model.generate, kwargs=generation_kwargs)
         thread.start()
         buffer = ""