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

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

zetasepic Qwen 73B
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"
Response includes
  • classification m1
  • files 42
  • benchmarks 16 entries
  • hub_downloads_all_time 1,575
  • providers 1
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=zetasepic
All 15 models by zetasepic
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
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)
How we label → About M1 →
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)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
2K
34 last 30d - cooling
Likes
5
Descendants
4
in 4 direct forks
Model age
23mo ago
created 2024-10-27
Available via
1 provider
featherless-ai
Downloads over time
Now1.6K→from2↑79,450%
05831.2K1.7K2 on Oct 23, 20241.6K on Oct 111.6K on Oct 10Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 23, 2024 → Oct 11 · 142 snapshots · spans 718 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 4 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↓ 34 4 forks
mradermacher/Qwen2.5-72B-Instruct-abliterated-v2-i1-GGUF↓ 786
mradermacher/Qwen2.5-72B-Instruct-abliterated-v2-GGUF↓ 498
featherless-ai-quants/zetasepic-Qwen2.5-72B-Instruct-abliterated-v2-GGUF↓ 290
blotfaba/Qwen-2.5-72B-Instruct-abliterated-v2-Q6_K.gguf↓ 103

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
Tags
transformers safetensors qwen2 text-generation chat conversational en base_model:Qwen/Qwen2.5-72B base_model:finetune:Qwen/Qwen2.5-72B license:other text-generation-inference endpoints_compatible

Related

Other by zetasepic
Qwen2.5-72B-Instruct-abliterated-GGUF 3K Qwen2.5-32B-Instruct-abliterated-v2-GGUF 2K Qwen2.5-72B-Instruct-abliterated-v2-GGUF 992 Qwen2.5-32B-Instruct-abliterated-v2 119 Qwen2.5-72B-Instruct-abliterated 80
Same base model
zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF 992 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
135 GB
Files
42
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-28 10:55
Source huggingface.co/zetasepic/Qwen2.5-72B-Instruct-abliterated-v2 ↗ Base model Qwen/Qwen2.5-72B ↗

Files by quantization

Auxiliary files 42 files 135 GB
model-00006-of-00031.safetensors 4.62 GB 307da985 download
model-00010-of-00031.safetensors 4.62 GB 25f47405 download
model-00014-of-00031.safetensors 4.62 GB 61f389c7 download
model-00018-of-00031.safetensors 4.62 GB acd92279 download
model-00022-of-00031.safetensors 4.62 GB 1175af87 download
model-00026-of-00031.safetensors 4.62 GB 31685018 download
model-00002-of-00031.safetensors 4.62 GB 64e567eb download
model-00005-of-00031.safetensors 4.45 GB 4dfedc09 download
model-00008-of-00031.safetensors 4.45 GB f0f30065 download
model-00009-of-00031.safetensors 4.45 GB 03212f3c download
model-00012-of-00031.safetensors 4.45 GB 73089d80 download
model-00013-of-00031.safetensors 4.45 GB 96207ad1 download
model-00016-of-00031.safetensors 4.45 GB 6cdfe678 download
model-00017-of-00031.safetensors 4.45 GB f82cff22 download
model-00020-of-00031.safetensors 4.45 GB 85caea6f download
model-00021-of-00031.safetensors 4.45 GB ddccd70d download
model-00024-of-00031.safetensors 4.45 GB 019140b4 download
model-00025-of-00031.safetensors 4.45 GB 23b3130b download
model-00028-of-00031.safetensors 4.45 GB d6978608 download
model-00029-of-00031.safetensors 4.45 GB 18c4ccef download
model-00004-of-00031.safetensors 4.45 GB 7eedea08 download
model-00007-of-00031.safetensors 4.45 GB b4809af0 download
model-00011-of-00031.safetensors 4.45 GB a9438118 download
model-00015-of-00031.safetensors 4.45 GB e568fe65 download
model-00019-of-00031.safetensors 4.45 GB 4c23e9e7 download
model-00023-of-00031.safetensors 4.45 GB ccfbd95a download
model-00027-of-00031.safetensors 4.45 GB bde2bd2c download
model-00003-of-00031.safetensors 4.45 GB 121f7de5 download
model-00001-of-00031.safetensors 4.24 GB bd7f06b8 download
model-00030-of-00031.safetensors 2.99 GB 97de3c84 download
model-00031-of-00031.safetensors 2.32 GB cdbc8f91 download
tokenizer.json 6.71 MB d24314ef download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 77.2 KB ac262537 download
tokenizer_config.json 7.13 KB 8adf747c download
.gitattributes 1.48 KB a6344aac download
README.md 860 B 0d2ee1fe download
config.json 726 B e02a3ff9 download
special_tokens_map.json 613 B ac23c0aa download
added_tokens.json 605 B 482ced46 download
generation_config.json 243 B 64d27602 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.

GGUF

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 2 versions

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

  1. 2024-10-28Update README.md4af6943860 B
    Loading...
  2. 2024-10-28Create README.md7055b9f778 B
    Loading...

Discussions 2 threads

  1. 2025-04-27PRImprove language tagopen1 💬#2
    Loading...
  2. 2025-02-02qwen 2.5 VL 72b abliterated please 🥹🥹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