← back to catalog · registered 2026-08-22 13:56

josephmayo/Fara-7B-Abliterated-v2-GGUF

Name: josephmayo/Fara-7B-Abliterated-v2-GGUF
Author: josephmayo

Your rig guess connected

? Why do I need an app?

Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/josephmayo%2FFara-7B-Abliterated-v2-GGUF"

Response includes

classification m8
files 11
hub_downloads_all_time 621
author_summary 4 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.

Confidence

MEDIUM

Inherited from base model

M1 Direct removal →

Why this label 3 signals

Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.

'abliterated' in name/tags
is_gguf=1
assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · lifetime

621

156 last 30d - stable

Likes

Model age

4mo ago

created 2026-05-25

Downloads over time

Jun 10 → Oct 12 · 58 snapshots · spans 124 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

josephmayo/Fara-7B-Abliterated-v2↓ 22 this lineage

josephmayo/Fara-7B-Abliterated-v2-GGUF↓ 156

Variants by this author 2 formats · 178 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

josephmayo/Fara-7B-Abliterated-v2-GGUF (this) GGUF 156
josephmayo/Fara-7B-Abliterated-v2 safetensors 22

Metadata

Files by quantization

Auxiliary files 11 files 23.6 GB

fara-7b-abliterated-q8_0.gguf	7.54 GB	7ffbb2a2	download
fara-7b-abliterated-q6_k.gguf	5.82 GB	9d14acd1	download
fara-7b-abliterated-q6_k-split-00001-of-00004.gguf	1.91 GB	6a0907df	download
fara-7b-abliterated-q6_k-split-00003-of-00004.gguf	1.91 GB	0b9892f7	download
fara-7b-abliterated-q4_k_m-split-00001-of-00003.gguf	1.91 GB	09b8302b	download
fara-7b-abliterated-q6_k-split-00002-of-00004.gguf	1.91 GB	817ac26b	download
fara-7b-abliterated-q4_k_m-split-00002-of-00003.gguf	1.90 GB	b8b1bff6	download
fara-7b-abliterated-q4_k_m-split-00003-of-00003.gguf	568 MB	bc39ae07	download
fara-7b-abliterated-q6_k-split-00004-of-00004.gguf	106 MB	aff4b882	download
.gitattributes	2.21 KB	77f62aa7	download
README.md	747 B	22dc3b32	download

README current version from Hugging Face

base_model: josephmayo/Fara-7B-Abliterated-v2
library_name: gguf
tags:

gguf
abliteration
refusal-removal
qwen2_5_vl
fara-7b
quantized: true

Fara-7B-Abliterated-v2-GGUF

GGUF quantizations of josephmayo/Fara-7B-Abliterated-v2.

Quant	File
Q4_K_M	ara-7b-abliterated-q4_k_m.gguf
Q6_K	ara-7b-abliterated-q6_k.gguf
Q8_0	ara-7b-abliterated-q8_0.gguf

Base

Original: microsoft/Fara-7B
Abliterated: josephmayo/Fara-7B-Abliterated-v2
Method: Arditi-2024 refusal-direction orthogonalization on the Qwen2.5-VL language tower.

Research artifact only. Not for harmful use.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

2026-05-25Add README2a4dc3b719 B
Loading...

josephmayo/Fara-7B-Abliterated-v2-GGUF

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now