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

v000000/L3-8B-Stheno-v3.2-abliterated

Name: v000000/L3-8B-Stheno-v3.2-abliterated
Author: v000000

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/v000000%2FL3-8B-Stheno-v3.2-abliterated"

Response includes

classification m5
files 15
benchmarks 11 entries
hub_downloads_all_time 1,236
providers 1
author_summary 5 models
readme_text full

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

Abliteration classifier · v1.0.0

Primary method

Mergekit merge

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.

merge tag / mergekit / dare-ties in tags or name
no unusual architecture pattern (regular merge)
abliterated marker present

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

36 last 30d - cooling

Likes

Descendants

in 3 direct forks

Model age

2.3y ago

created 2024-07-09

Available via

1 provider

featherless-ai

Downloads over time

Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Benchmarks

Portrait before abliteration

Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.

Benchmark	Score	Source
Entertainment	1	UGI
Hazardous	1.2	UGI
Natural Intelligence	12.61	UGI
Political lean	-11.9%	UGI
Sensitive-Info	12.09	UGI
SocPol	1.5	UGI
UGI	20.56	UGI
Willingness (10)	3.8	UGI
W10-Adherence	3.5	UGI
W10-Direct	4	UGI
Writing	30.44	UGI

Genealogy 3 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.

Sao10K/L3-8B-Stheno-v3.2 this lineage

v000000/L3-8B-Stheno-v3.2-abliterated↓ 36 3 forks

mradermacher/L3-8B-Stheno-v3.2-abliterated-GGUF↓ 2,316

mradermacher/L3-8B-Stheno-v3.2-abliterated-i1-GGUF↓ 1,694

RogerS-01/L3-8B-Stheno-v3.2-abliterated-AWQ↓ 7

Metadata

Files by quantization

Auxiliary files 15 files 29.9 GB

model-00003-of-00007.safetensors	4.66 GB	15891c5f	download
model-00004-of-00007.safetensors	4.66 GB	82e9fcae	download
model-00006-of-00007.safetensors	4.66 GB	d67e4a23	download
model-00001-of-00007.safetensors	4.65 GB	35ca04f6	download
model-00002-of-00007.safetensors	4.58 GB	52f69733	download
model-00005-of-00007.safetensors	4.50 GB	c0fb2cff	download
model-00007-of-00007.safetensors	2.22 GB	784aa8ce	download
tokenizer.json	8.66 MB	b197f72e	download
tokenizer_config.json	49.8 KB	1bfd1146	download
model.safetensors.index.json	22.3 KB	05459844	download
.gitattributes	1.48 KB	a6344aac	download
README.md	1.39 KB	adf45b12	download
config.json	716 B	212b12dc	download
special_tokens_map.json	296 B	02ee80b6	download
mergekit_config.yml	159 B	6f60e03f	download

README current version from Hugging Face

base_model:

Sao10K/L3-8B-Stheno-v3.2
grimjim/Llama-3-Instruct-abliteration-LoRA-8B
library_name: transformers
tags:
mergekit
merge
llama

Simply "Llama3-Stheno-v3.2-Zeta" by Sao10K with abliteration adaption from grimjim

Tested: Succesful abliteration.

mradermacher quants below:

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Sao10K/L3-8B-Stheno-v3.2 + grimjim/Llama-3-Instruct-abliteration-LoRA-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/L3-8B-Stheno-v3.2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1.0
merge_method: linear
dtype: float32

README history 9 versions

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

2024-07-11Update README.mdddb17f11.4 KB
Loading...
2024-07-11Update README.mdeb655141.4 KB
Loading...
2024-07-11Update README.mdaf3e3681.3 KB
Loading...
2024-07-11Update README.md448d5ab1.3 KB
Loading...
2024-07-11Update README.md33ea9a41.2 KB
Loading...
2024-07-09Update README.mded17bf91.1 KB
Loading...
2024-07-09Update README.md8557cbb1.1 KB
Loading...
2024-07-09Update README.md14de2a91.1 KB
Loading...
2024-07-09Upload folder using huggingface_hubcb1674e915 B
Loading...

Discussions 1 thread

2024-08-22[Request]: L3-8B-Stheno-v3.4-abliterated?closed2 💬#1
Loading...

Continue on Hugging Face →