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

zypcastles/QwQ-32B-Instruct-abliterated

Name: zypcastles/QwQ-32B-Instruct-abliterated
Author: zypcastles

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/zypcastles%2FQwQ-32B-Instruct-abliterated"

Response includes

classification m5
files 25
benchmarks 11 entries
hub_downloads_all_time 114
author_summary 1 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

114

21 last 30d - stable

Likes

Descendants

in 3 direct forks

Model age

22mo ago

created 2024-12-10

Downloads over time

Dec 11, 2024 → Oct 12 · 136 snapshots · spans 670 days

Benchmarks

Benchmark	Score	Source
Entertainment	1.4	UGI
Hazardous	3.5	UGI
Natural Intelligence	19.94	UGI
Political lean	-8.8%	UGI
Sensitive-Info	20.28	UGI
SocPol	1.6	UGI
UGI	36.02	UGI
Willingness (10)	6.8	UGI
W10-Adherence	6.5	UGI
W10-Direct	7	UGI
Writing	29.94	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.

huihui-ai/Qwen2.5-32B-Instruct-abliterated↓ 4,927 this lineage

zypcastles/QwQ-32B-Instruct-abliterated↓ 21 3 forks

mradermacher/QwQ-32B-Instruct-abliterated-i1-GGUF↓ 883

mradermacher/QwQ-32B-Instruct-abliterated-GGUF↓ 464

Apel-sin/qwq-32b-instruct-abliterated-exl2

Metadata

Files by quantization

Auxiliary files 25 files 61.0 GB

model-00002-of-00014.safetensors	4.65 GB	7c275647	download
model-00001-of-00014.safetensors	4.61 GB	5ceb23a4	download
model-00003-of-00014.safetensors	4.54 GB	68f7dcf5	download
model-00005-of-00014.safetensors	4.54 GB	95406840	download
model-00007-of-00014.safetensors	4.54 GB	55d0f553	download
model-00009-of-00014.safetensors	4.54 GB	1e302d9f	download
model-00011-of-00014.safetensors	4.54 GB	b778b641	download
model-00004-of-00014.safetensors	4.54 GB	c688c581	download
model-00006-of-00014.safetensors	4.54 GB	d18a38d2	download
model-00008-of-00014.safetensors	4.54 GB	b4cfda94	download
model-00010-of-00014.safetensors	4.54 GB	b9631a47	download
model-00012-of-00014.safetensors	4.54 GB	83cb62e7	download
model-00013-of-00014.safetensors	4.54 GB	099a515a	download
model-00014-of-00014.safetensors	1.82 GB	2149070a	download
tokenizer.json	10.9 MB	9c5ae00e	download
vocab.json	2.65 MB	4783fe10	download
merges.txt	1.59 MB	31349551	download
model.safetensors.index.json	58.8 KB	d4f5130a	download
tokenizer_config.json	7.13 KB	2b27f5a9	download
.gitattributes	1.53 KB	52373fe2	download
README.md	1.06 KB	26793115	download
config.json	745 B	4d13da9f	download
special_tokens_map.json	613 B	ac23c0aa	download
added_tokens.json	605 B	482ced46	download
mergekit_config.yml	239 B	5db3e006	download

README current version from Hugging Face

base_model:

huihui-ai/Qwen2.5-32B-Instruct-abliterated
huihui-ai/QwQ-32B-Preview-abliterated
library_name: transformers
tags:
mergekit
merge

This model is created to fix the instruction-following flaws presented in the QwQ model.

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: huihui-ai/QwQ-32B-Preview-abliterated
  - model: huihui-ai/Qwen2.5-32B-Instruct-abliterated
merge_method: slerp
base_model: huihui-ai/QwQ-32B-Preview-abliterated
parameters:
  t: [0.1, 0.2, 0.3, 0.3, 0.2]
dtype: bfloat16

README history 4 versions

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

2024-12-12Update README.mdbac71ff1.1 KB
Loading...
2024-12-10Update README.md4b5e2011.1 KB
Loading...
2024-12-10Update README.mdeb8885c1 KB
Loading...
2024-12-10Upload folder using huggingface_hub4cea955988 B
Loading...

Discussions 1 thread

2024-12-11Exllamav2 quant neededclosed4 💬#1
Loading...

Continue on Hugging Face →