gemma-3-27b-it-heretic-v1.2-GGUF

grayarea/gemma-3-27b-it-heretic-v1.2-GGUF

gemma-3-27b-it-heretic-v1.2-GGUF is a machine learning model from grayarea. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

This is a decensored version of gemma-3-27b-it, made using Heretic v1.2.0 focusing on zero refusals with low KL divergence

Downloads · 30 days

14% of all-time downloads

All-time downloads

482

Public

Repo size

99.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf99.3 GB · 100%

At a glance

Access: Public
Created: Mar 8, 2026
Updated: Mar 8, 2026
SHA: ebc7aa2d

Base models

grayarea/gemma-3-27b-it-heretic-v1.2

Model card

From the Hugging Face model README

This is a decensored version of gemma-3-27b-it, made using Heretic v1.2.0 focusing on zero refusals with low KL divergence

KL Divergence

Metric	This Model	Original Model
KL divergence	0.0539	0 (by definition)
Refusals	0/108	107/108

Abliteration parameters

Zero refusals with KL divergence of 0.0539
Custom heretic training dataset
Model targetted heretic configuration
Abliterated with MPOA enabled (Magnitude-Preserving Orthogonal Ablation)
Full row renormalization
Winsorization Quantile 0.997

Relative Perplexity

Quant	Filename	PPL ± Error
Q8_0	gemma-3-27b-it-Q8_0.gguf (original baseline)	6.5517 +/- 0.04674
Q8_0	gemma-3-27b-it-heretic-v1.2-Q8_0.gguf	6.5510 +/- 0.04666
Q4_K_M	gemma-3-27b-it-heretic-v1.2-Q4_K_M.gguf	6.6245 +/- 0.04704

Benchmark Comparison

Benchmark	gemma-3-27b-it-Q8_0.gguf	gemma-3-27b-it-Q4_K_M.gguf	gemma-3-27b-it-heretic-v1.2-Q4_K_M.gguf
Perplexity (Wikitext-2)	6.5517	6.6226	6.6245
HellaSwag	81.75%	81.75%	80.50%
Winogrande	76.24%	76.32%	76.40%
ARC-Challenge	57.86%	58.86%	59.53%
MMLU	45.35%	46.58%	45.41%

*Note: MMLU benchmark has moral_scenarios, moral_disputes, business_ethics, professional_law and jurisprudence subjects removed. *

Created: Mar 8, 2026
Updated: Mar 8, 2026