200 tokens max

app.py

@@ -89,7 +89,7 @@ def bot_streaming(message, history):
 
   inputs = processor(text=prompt, images=image, videos=video, return_tensors="pt").to("cuda", torch.float16)
   streamer = TextIteratorStreamer(processor, **{"max_new_tokens": 200, "skip_special_tokens": True})
-  generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=100)
+  generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=200)
   generated_text = ""
 
   thread = Thread(target=model.generate, kwargs=generation_kwargs)