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

RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-awq

Name: RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-awq
Author: RichardErkhov

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/RichardErkhov%2Fhuihui-ai_-_Llama-3.2-1B-Instruct-abliterated-awq"

Response includes

classification m1
files 8
hub_downloads_all_time 49
author_summary 257 models
readme_text full

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

Abliteration classifier · v1.0.0

Primary method

Direct removal

No other method signals detected in this model.

Confidence

MEDIUM

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=0 (base model)
no specific method indicators - defaulting to M1 (most common)

Refusal direction extracted via

Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗

Confidence

MEDIUM

Why we say so

primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)

Downloads · lifetime

8 last 30d - stable

Likes

Model age

22mo ago

created 2024-11-22

Downloads over time

Nov 20, 2024 → Oct 11 · 138 snapshots · spans 690 days

Variants by this author 2 formats · 2K downloads combined

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

RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf GGUF 2K
RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-awq (this) AWQ 8

Metadata

Files by quantization

Auxiliary files 8 files 1000 MB

model.safetensors	983 MB	a81ae634	download
tokenizer.json	16.4 MB	6b9e4e7f	download
tokenizer_config.json	53.4 KB	610743cb	download
README.md	1.70 KB	609d09a2	download
.gitattributes	1.53 KB	52373fe2	download
config.json	1.08 KB	cd0bc0a0	download
special_tokens_map.json	439 B	344c8261	download
generation_config.json	184 B	144bd5f2	download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-1B-Instruct-abliterated - AWQ

Model creator: https://huggingface.co/huihui-ai/
Original model: https://huggingface.co/huihui-ai/Llama-3.2-1B-Instruct-abliterated/

Original model description:

library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:

abliterated
uncensored

🦙 Llama-3.2-1B-Instruct-abliterated

This is an uncensored version of Llama 3.2 1B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark	Llama-3.2-1B-Instruct	Llama-3.2-1B-Instruct-abliterated
IF_Eval	58.50	56.88
MMLU Pro	16.35	14.35
TruthfulQA	43.08	38.96
BBH	33.75	31.83
GPQA	25.96	26.39
The script used for evaluation can be found inside this repository under /eval.sh, or click here

README history 1 version

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

2024-11-22uploaded readmee49518b1.7 KB
Loading...

RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-awq

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now