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

retraining pairwise head on different data mixture different regularization during rl training

draft_pw_jq_self-fit-3_indexed_v2.safetensors

self-fit-3

dpvo_2

dpvo_1

llrrw_4

llrrw_3

llrrw_2

llrrw_1

siglip

rapid

self

Files with SHA256: ba96415e6e8e120d6a2038f261727f516095d6e8866b4018c932449bf621646d