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

zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF

zetasepic Qwen 72B GGUF 33K ctx
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/zetasepic%2FQwen2.5-72B-Instruct-abliterated-v2-GGUF"
Response includes
  • classification m8
  • files 11
  • benchmarks 16 entries
  • hub_downloads_all_time 24,569
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=zetasepic
All 15 models by zetasepic
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
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
How we label → About M8 →
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.

What is a refusal direction? →
Downloads · lifetime
25K
992 last 30d - cooling
Likes
4
Model age
23mo ago
created 2024-10-28
Downloads over time
Now24.8K→from145↑17,032%
09.1K18.2K27.3K145 on Oct 23, 202424.8K on Oct 12Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 23, 2024 → Oct 12 · 143 snapshots · spans 719 days

Benchmarks

Benchmark Score Source
Entertainment 2 UGI
Hazardous 4.1 UGI
Natural Intelligence 19.14 UGI
Political lean -3.8% UGI
Sensitive-Info 28.63 UGI
SocPol 3 UGI
UGI 44.09 UGI
Willingness (10) 7.5 UGI
W10-Adherence 5 UGI
W10-Direct 10 UGI
Writing 28 UGI
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
BBH average 0.6161629264496044 OpenLLM-v2
IFEval instruct 0.46882494004796166 OpenLLM-v2
IFEval-Prompt 0.3585951940850277 OpenLLM-v2
MATH lvl 5 0.3610271903323263 OpenLLM-v2
MMLU-Pro 0.5968251329787234 OpenLLM-v2

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.

Qwen/Qwen2.5-72B this lineage
zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF↓ 992

Variants by this author 2 formats · 1K downloads combined

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

Metadata

License
other
Languages
en
Quantizations
IQ3 IQ4 Q2_K Q3_K Q4_K
Tags
transformers gguf chat text-generation en base_model:Qwen/Qwen2.5-72B base_model:quantized:Qwen/Qwen2.5-72B license:other endpoints_compatible region:us conversational

Related

Other by zetasepic
Qwen2.5-72B-Instruct-abliterated-GGUF 3K Qwen2.5-32B-Instruct-abliterated-v2-GGUF 2K Qwen2.5-32B-Instruct-abliterated-v2 119 Qwen2.5-72B-Instruct-abliterated 80 Qwen2.5-32B-Instruct-abliterated-pass2-gguf 71
Same base model
zetasepic/Qwen2.5-72B-Instruct-abliterated-v2 34 matatonic/Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2 26 zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-5.0bpw-exl2 21 matatonic/Qwen2.5-72B-Instruct-abliterated-v2-4.5bpw-exl2 18
Total size
309 GB
Files
11
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2024-10-28 10:52
Source huggingface.co/zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF ↗ Base model Qwen/Qwen2.5-72B ↗

Files by quantization

Q4_K 1 file 44.2 GB
Qwen2.5-72B-Instruct-abliterated-v2-Q4_K_M.gguf 44.2 GB 620d0a8d download
IQ4 1 file 37.4 GB
Qwen2.5-72B-Instruct-abliterated-v2-IQ4_XS.gguf 37.4 GB 771d563e download
Q3_K 1 file 35.1 GB
Qwen2.5-72B-Instruct-abliterated-v2-Q3_K_M.gguf 35.1 GB 61c5545a download
IQ3 1 file 33.1 GB
Qwen2.5-72B-Instruct-abliterated-v2-IQ3_M.gguf 33.1 GB bf887422 download
Q2_K 1 file 27.8 GB
Qwen2.5-72B-Instruct-abliterated-v2-Q2_K.gguf 27.8 GB 3818f700 download
Auxiliary files 6 files 132 GB
Qwen2.5-72B-Instruct-abliterated-v2-Q8_0-00001-of-00002.gguf 44.7 GB e891c9b8 download
Qwen2.5-72B-Instruct-abliterated-v2-Q6_K-00001-of-00002.gguf 44.5 GB 4aebb9e5 download
Qwen2.5-72B-Instruct-abliterated-v2-Q8_0-00002-of-00002.gguf 27.3 GB 9ceb9f91 download
Qwen2.5-72B-Instruct-abliterated-v2-Q6_K-00002-of-00002.gguf 15.5 GB 3241c1bf download
.gitattributes 2.27 KB 4e0b4c0c download
README.md 778 B 91ed7fae download

README current version from Hugging Face

license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
language:

  • en
    pipeline_tag: text-generation
    base_model: Qwen/Qwen2.5-72B
    tags:
  • chat
    library_name: transformers

Abliterated version of Qwen/Qwen2.5-72B-Instruct, utilizing code from refusal_direction.

For more information about the Abliterated technique, refer to this article and check out @FailSpy.

Try harder to remove admonition and moral appeal

This model is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.

README history 3 versions

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

  1. 2024-10-28Update README.md973d33b778 B
    Loading...
  2. 2024-10-28Update README.md9078204771 B
    Loading...
  3. 2024-10-28Create README.md12fe971853 B
    Loading...

Discussions 2 threads

  1. 2025-04-27PRImprove language tagopen1 💬#2
    Loading...
  2. 2024-11-19Is the model finetune after abliteration?open1 💬#1
    Loading...

Continue on Hugging Face →

Catalog is the map. Apps are the tools.

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

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration