Fine-tune Multi-modal Vision and Language Models

and a one-click API template for Mamba!

Fine-tune Llava 1.6

- How do image + language models work?
- Which is better? Open source Llava 1.6 OR GPT4 Vision?
- How to fine-tune Llava 1.6 on a custom image/text dataset?

Check out the full vid:

Mamba TGI API One-click Template

You can now set up an inference endpoint for Mamba style models!

That’s it for this week, Ronan

Links:

• One-click Template Repo

• ADVANCED Vision Repo

• ADVANCED Fine Tuning Repo

• ADVANCED Inference Repo

• FUNCTION Calling Models