I'm looking forward to see that the tutorials related to VL (image-text-to-text) added to the project!

[Tegala]

As stated in the title.

[qibin0506]

You can take a look at my project, which supports VLM
https://github.com/qibin0506/llm_model
https://github.com/qibin0506/llm_trainer

[Tegala]

Thanks for your code!

[rasbt]

@Tegala Thanks for suggesting. I am currently working on reasoning techniques, but yes, eventually I plan to add vision related content.

[Tegala]

Thanks for this repo, it’s incredibly helpful for learning!