Downloads · 30 days
1
5% of all-time downloads
judgebench-brand-dial-lora
Gupta28/judgebench-brand-dial-lora
judgebench-brand-dial-lora is a machine learning model from Gupta28. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Part of judgecliff. A rank-16 LoRA for black-forest-labs/FLUX.1-dev (ai-toolkit sdtrainer, trigger word rhodestyle, 3000 steps, fp16) trained on rhode brand images. It is not an attack or a judge: it is the Phase-1 me…
All-time downloads
19
Public
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 30, 2026
- SHA
- 2edfc006
Base models
Model card
From the Hugging Face model README
judgecliff brand-ness dial (FLUX.1-dev LoRA, rhode)
Part of judgecliff. A rank-16 LoRA for black-forest-labs/FLUX.1-dev
(ai-toolkit sd_trainer, trigger word rhodestyle, 3000 steps, fp16) trained on
rhode brand images. It is not an attack or a judge: it is the Phase-1
measurement instrument — sweeping LoRA strength (and using the step checkpoints
rhode_lora_000000500 … rhode_lora_000002500 alongside the final weights) produces a
graded "brand-ness dial" used to test whether each judge ranks brand intensity
monotonically (the dial-Spearman column of the report card).
Training config: config.yaml. Full protocol: https://github.com/amargupta0428/judgecliff.
- Created
- Jul 9, 2026
- Updated
- Jul 30, 2026