Could not find proper documentation for finetuning supported models

[Blaizzy]

Discussed in https://github.com/Blaizzy/mlx-vlm/discussions/476

^{Originally posted by avishekjana August 27, 2025} Hi,

I’m trying to fine-tune LLaMA 3.2 Vision and Qwen 2 VL, but the main challenge I’m facing is the lack of clear documentation on data preparation. This is causing several issues during the process.

In the LORA.md file, could you please provide a notebook or detailed data preparation guidelines (at least for the supported models)? That would be extremely helpful.

Thanks in advance!