LoRAs trained using DRaFT-like post-RL using Siglip/Dino Don't expect sensible results on any other model than <a target="_blank" rel="ugc" href="https://civarchive.com/models/1772667/indexed">indexed v2</a> These are just experiments. I will often not avoid over-training and forgo stronger regularization as I am more so looking for what effects are most prominent for varying data regimes.

post_rl_indexed_v2_lora

pairwise head fitted to <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Rapidata/open-image-preferences-v1-more-results-binarized">https://huggingface.co/datasets/Rapidata/open-image-preferences-v1-more-results-binarized</a>

Files with SHA256: 0da7f872a0251762810e5b9271fb75291bce7fb56ee9d3aa0f478c25cce74aca