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

RichardErkhov/trollek_-_Qwen2-1.5B-Instruct-Abliterated-gguf

Name: RichardErkhov/trollek_-_Qwen2-1.5B-Instruct-Abliterated-gguf
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%2Ftrollek_-_Qwen2-1.5B-Instruct-Abliterated-gguf"

Response includes

classification m8
files 24
hub_downloads_all_time 5,186
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

Repackaging (quantization)

No other method signals detected in this model.

Confidence

MEDIUM

Why this label 2 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.

author=richarderkhov (M8 quantization producer)
is_gguf=1

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

598 last 30d - stable

Likes

Model age

2.3y ago

created 2024-07-05

Downloads over time

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

Metadata

Quantizations

IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0

Files by quantization

Q8_0 1 file 1.53 GB

Qwen2-1.5B-Instruct-Abliterated.Q8_0.gguf

1.53 GB

5ae5a3da

download

Q6_K 1 file 1.19 GB

Qwen2-1.5B-Instruct-Abliterated.Q6_K.gguf

1.19 GB

84c3313d

download

Q5 2 files 2.12 GB

Qwen2-1.5B-Instruct-Abliterated.Q5_1.gguf	1.10 GB	b213d576	download
Qwen2-1.5B-Instruct-Abliterated.Q5_0.gguf	1.02 GB	9e9d12a5	download

Q5_K 3 files 3.12 GB

Qwen2-1.5B-Instruct-Abliterated.Q5_K.gguf	1.05 GB	539c9ae7	download
Qwen2-1.5B-Instruct-Abliterated.Q5_K_M.gguf	1.05 GB	539c9ae7	download
Qwen2-1.5B-Instruct-Abliterated.Q5_K_S.gguf	1.02 GB	acbd3463	download

Q4 2 files 1.82 GB

Qwen2-1.5B-Instruct-Abliterated.Q4_1.gguf	970 MB	6ccca1a0	download
Qwen2-1.5B-Instruct-Abliterated.Q4_0.gguf	892 MB	dee5d217	download

Q4_K 3 files 2.71 GB

Qwen2-1.5B-Instruct-Abliterated.Q4_K.gguf	940 MB	64374710	download
Qwen2-1.5B-Instruct-Abliterated.Q4_K_M.gguf	940 MB	64374710	download
Qwen2-1.5B-Instruct-Abliterated.Q4_K_S.gguf	897 MB	5011f572	download

IQ4 2 files 1.72 GB

Qwen2-1.5B-Instruct-Abliterated.IQ4_NL.gguf	898 MB	6d23924a	download
Qwen2-1.5B-Instruct-Abliterated.IQ4_XS.gguf	860 MB	a705266f	download

Q3_K 4 files 3.06 GB

Qwen2-1.5B-Instruct-Abliterated.Q3_K_L.gguf	839 MB	a43511f4	download
Qwen2-1.5B-Instruct-Abliterated.Q3_K.gguf	786 MB	ea671ee5	download
Qwen2-1.5B-Instruct-Abliterated.Q3_K_M.gguf	786 MB	ea671ee5	download
Qwen2-1.5B-Instruct-Abliterated.Q3_K_S.gguf	726 MB	7c72ce26	download

IQ3 3 files 2.11 GB

Qwen2-1.5B-Instruct-Abliterated.IQ3_M.gguf	741 MB	66723938	download
Qwen2-1.5B-Instruct-Abliterated.IQ3_S.gguf	727 MB	91234f0b	download
Qwen2-1.5B-Instruct-Abliterated.IQ3_XS.gguf	698 MB	240ea0b3	download

Q2_K 1 file 645 MB

Qwen2-1.5B-Instruct-Abliterated.Q2_K.gguf

645 MB

d7989596

download

Auxiliary files 2 files 8.60 KB

README.md	5.42 KB	8a3093ac	download
.gitattributes	3.18 KB	8b4e2fe6	download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2-1.5B-Instruct-Abliterated - GGUF

Model creator: https://huggingface.co/trollek/
Original model: https://huggingface.co/trollek/Qwen2-1.5B-Instruct-Abliterated/

Name	Quant method	Size
Qwen2-1.5B-Instruct-Abliterated.Q2_K.gguf	Q2_K	0.63GB
Qwen2-1.5B-Instruct-Abliterated.IQ3_XS.gguf	IQ3_XS	0.68GB
Qwen2-1.5B-Instruct-Abliterated.IQ3_S.gguf	IQ3_S	0.71GB
Qwen2-1.5B-Instruct-Abliterated.Q3_K_S.gguf	Q3_K_S	0.71GB
Qwen2-1.5B-Instruct-Abliterated.IQ3_M.gguf	IQ3_M	0.72GB
Qwen2-1.5B-Instruct-Abliterated.Q3_K.gguf	Q3_K	0.77GB
Qwen2-1.5B-Instruct-Abliterated.Q3_K_M.gguf	Q3_K_M	0.77GB
Qwen2-1.5B-Instruct-Abliterated.Q3_K_L.gguf	Q3_K_L	0.82GB
Qwen2-1.5B-Instruct-Abliterated.IQ4_XS.gguf	IQ4_XS	0.84GB
Qwen2-1.5B-Instruct-Abliterated.Q4_0.gguf	Q4_0	0.87GB
Qwen2-1.5B-Instruct-Abliterated.IQ4_NL.gguf	IQ4_NL	0.88GB
Qwen2-1.5B-Instruct-Abliterated.Q4_K_S.gguf	Q4_K_S	0.88GB
Qwen2-1.5B-Instruct-Abliterated.Q4_K.gguf	Q4_K	0.92GB
Qwen2-1.5B-Instruct-Abliterated.Q4_K_M.gguf	Q4_K_M	0.92GB
Qwen2-1.5B-Instruct-Abliterated.Q4_1.gguf	Q4_1	0.95GB
Qwen2-1.5B-Instruct-Abliterated.Q5_0.gguf	Q5_0	1.02GB
Qwen2-1.5B-Instruct-Abliterated.Q5_K_S.gguf	Q5_K_S	1.02GB
Qwen2-1.5B-Instruct-Abliterated.Q5_K.gguf	Q5_K	1.05GB
Qwen2-1.5B-Instruct-Abliterated.Q5_K_M.gguf	Q5_K_M	1.05GB
Qwen2-1.5B-Instruct-Abliterated.Q5_1.gguf	Q5_1	1.1GB
Qwen2-1.5B-Instruct-Abliterated.Q6_K.gguf	Q6_K	1.19GB
Qwen2-1.5B-Instruct-Abliterated.Q8_0.gguf	Q8_0	1.53GB

Original model description:

license: apache-2.0
tags:

not-for-all-audiences

This is an abliterated version of Qwen2-1.5B-Instruct using the same procedure as augmxnt/Qwen2-7B-Instruct-deccp with their code on Github with some added lines from mlabonne/harmful_behaviors to the harmful.txt file.

I have not done anything else to the model. Yet.

README history 1 version

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

2024-07-05uploaded readme9f32a3e5.4 KB
Loading...

RichardErkhov/trollek_-_Qwen2-1.5B-Instruct-Abliterated-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

Repackaging (quantization)

Metadata

Related

Files by quantization

README current version from Hugging Face

Original model description:

README history 1 version

Run models on your own machine, not in the cloud.