RimDialogue-3B-v1-absolute-heresy

MuXodious/RimDialogue-3B-v1-absolute-heresy

RimDialogue-3B-v1-absolute-heresy is a machine learning model from MuXodious. 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 RimDialogue-3B-v1 fine-tune, produced through P-E-W's Heretic (v1.1.0) abliteration engine merged with the Magnitude-Preserving Orthogonal Ablation PR.

Downloads · 30 days

4% of all-time downloads

All-time downloads

428

Public

Parameters

3.2B

6.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.4 GB · 100%

At a glance

Model type: llama
Access: Public
Created: Feb 1, 2026
Updated: Feb 3, 2026
SHA: eb1bd24a

Base models

TheDrummer/RimDialogue-3B-v1

Model card

From the Hugging Face model README

This is a RimDialogue-3B-v1 fine-tune, produced through P-E-W's Heretic (v1.1.0) abliteration engine merged with the Magnitude-Preserving Orthogonal Ablation PR.

Note: I needed this as an avid RimWorld enjoyer. Alternative mod: RimTalk

Heretication Results

Score Metric	Value	Parameter	Value
Refusals	4/100	direction_index	13.50
KL Divergence	0.0146	attn.o_proj.max_weight	1.59
Initial Refusals	91/100	attn.o_proj.max_weight_position	22.58
		attn.o_proj.min_weight	1.17
		attn.o_proj.min_weight_distance	13.77
		mlp.down_proj.max_weight	1.32
		mlp.down_proj.max_weight_position	23.23
		mlp.down_proj.min_weight	0.72
		mlp.down_proj.min_weight_distance	13.33

Degree of Heretication

The Heresy Index weighs the resulting model's corruption by the process (KL Divergence) and its abolition of doctrine (Refusals) for a final verdict in classification.

Index Entry	Classification	Analysis
	Absolute Heresy	Less than 10/100 Refusals and 0.10 KL Divergence
	Tainted Heresy	Around 25-11/100 Refusals and/or -0.20-0.11 KL Divergence
	Impotent Heresy	Anything above 25/100 Refusals and 0.21 KL Divergence