mtensor commited on
Commit
5cc174c
1 Parent(s): 09b15be

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -1
app.py CHANGED
@@ -48,7 +48,9 @@ with gr.Blocks(css=css) as demo:
48
  <h3><a href="https://hf.co/adept/fuyu-8b">Fuyu-8B</a> is a multimodal model that supports a variety of tasks combining text and image prompts.</h3>
49
  For example, you can use it for captioning by asking it to describe an image. You can also ask it questions about an image, a task known as Visual Question Answering, or VQA. This demo lets you explore captioning and VQA, with more tasks coming soon :)
50
  Learn more about the model in <a href="https://www.adept.ai/blog/fuyu-8b">our blog post</a>.
51
- <strong>Note: This is a raw model release. We have not added further instruction-tuning, postprocessing or sampling strategies to control for undesirable outputs. You should expect to have to fine-tune the model for your use-case!</strong>
 
 
52
  <h3>Play with Fuyu-8B in this demo! 💬</h3>
53
  """
54
  )
 
48
  <h3><a href="https://hf.co/adept/fuyu-8b">Fuyu-8B</a> is a multimodal model that supports a variety of tasks combining text and image prompts.</h3>
49
  For example, you can use it for captioning by asking it to describe an image. You can also ask it questions about an image, a task known as Visual Question Answering, or VQA. This demo lets you explore captioning and VQA, with more tasks coming soon :)
50
  Learn more about the model in <a href="https://www.adept.ai/blog/fuyu-8b">our blog post</a>.
51
+ <br>
52
+ <br>
53
+ <strong>Note: This is a raw model release. We have not added further instruction-tuning, postprocessing or sampling strategies to control for undesirable outputs. The model may hallucinate, and you should expect to have to fine-tune the model for your use-case!</strong>
54
  <h3>Play with Fuyu-8B in this demo! 💬</h3>
55
  """
56
  )