Downloads · 30 days
67
17% of all-time downloads
Gemma-4-1-E4B-it-heretic
eshucode/Gemma-4-1-E4B-it-heretic
Gemma-4-1-E4B-it-heretic is a any-to-any model from eshucode. Use it for the any-to-any task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Abliterated (refusal-direction ablated) build of the refreshed Gemma-4 E4B-it.
All-time downloads
386
Public
Parameters
7.9B
15.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors15.9 GB · 100%
At a glance
- Task
- Any-to-Any
- License
- apache-2.0
- Model type
- gemma4
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- 152be195
Base models
Model card
From the Hugging Face model README
Gemma-4-1-E4B-it (heretic)
Abliterated (refusal-direction ablated) build of the refreshed Gemma-4 E4B-it.
"Gemma-4-1" is our label for the 2026-07-20 refreshed Gemma-4 weights
(post chat-template / tool-calling fixes) — it is not an official Google
release name. The true base is google/gemma-4-E4B-it at commit ee0ef6023621cff504d758262d4e04895a5af4a2.
Decensored with heretic (optimized abliteration; dual objective: minimise refusals + minimise KL from the base). Base license Apache 2.0. No fine-tuning; weights-only intervention.
This build (Pareto trial 198)
- Refusals 25/100, KL divergence 0.0219 on heretic's harmful_behaviors eval — the low-KL knee of the 200-trial front (near-max refusal reduction, minimal capability drift).
Reproduce any trial
heretic-study.jsonl in this repo is the complete 200-trial Optuna study. To
publish a more-aggressive point (e.g. trial 106: 23/100 refusals, KL 0.133):
mkdir checkpoints && cp heretic-study.jsonl checkpoints/google--gemma-4-E4B-it.jsonl
heretic --model google/gemma-4-E4B-it --study-checkpoint-dir checkpoints
This reopens the Pareto menu with zero re-search.
- Task
- Any-to-Any
- Type
- gemma4
- License
- apache-2.0
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026