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

preference head trained on base google/siglip2-so400m-patch16-naflex instead of joyquality DRaFT-K (K=5)

draft_pw_siglip2_so400m_naflex_mix_indexed_v2.safetensors

siglip

dpvo_2

dpvo_1

llrrw_4

llrrw_3

llrrw_2

llrrw_1

self-fit-3

rapid

self

Files with SHA256: 0971c68d0b2d2f2bea2d26a21a9a4916a5aa54a47072ea4a9647b55999484504