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

zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-5.0bpw-exl2

zetasepic Qwen 72B
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-v2-5.0bpw-exl2"
Response includes
  • classification m1
  • files 17
  • benchmarks 5 entries
  • hub_downloads_all_time 119
  • 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
119
21 last 30d - stable
Likes
0
Model age
23mo ago
created 2024-10-30
Downloads over time
Now130→from4↑3,150%
048951434 on Mar 5, 2025130 on Oct 11Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 5, 2025 → Oct 11 · 123 snapshots · spans 585 days

Benchmarks

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-v2-5.0bpw-exl2↓ 21

Metadata

License
other
Languages
en
Tags
transformers safetensors qwen2 text-generation chat conversational en base_model:Qwen/Qwen2.5-72B base_model:quantized: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 zetasepic/Qwen2.5-72B-Instruct-abliterated-v2 34 matatonic/Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2 26 matatonic/Qwen2.5-72B-Instruct-abliterated-v2-4.5bpw-exl2 18
Total size
44.1 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-30 17:11
Source huggingface.co/zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-5.0bpw-exl2 ↗ Base model Qwen/Qwen2.5-72B ↗

Files by quantization

Auxiliary files 17 files 44.1 GB
output-00001-of-00006.safetensors 7.97 GB 46dfb2c9 download
output-00002-of-00006.safetensors 7.97 GB 10dc9c23 download
output-00004-of-00006.safetensors 7.95 GB 9fd64d7e download
output-00003-of-00006.safetensors 7.95 GB 485e109a download
output-00005-of-00006.safetensors 7.85 GB 1cf78a94 download
output-00006-of-00006.safetensors 4.38 GB 4b7f9d73 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
config.json 1.02 KB 173254f8 download
README.md 860 B 0d2ee1fe 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 1 version

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

  1. 2024-10-30Upload folder using huggingface_hubabf08d8860 B
    Loading...

Discussions 1 thread

  1. 2025-04-27PRImprove language tagopen1 💬#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