Sign In

post_rl_indexed_v2_lora

192

Updated: Jan 7, 2026

style

Not recently loaded

Download

1 variant available

SafeTensor

354.62 MB

Verified:

Type
LoRA
Stats

91

11

8

Reviews
Published

Dec 3, 2025

Base Model
Hash
AutoV20971C68D0B

LoRAs trained using DRaFT-like post-RL using Siglip/Dino

Don't expect sensible results on any other model than indexed v2

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.