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

nbeerbower/Qwen2.5-32B-abliterated-LORA

nbeerbower Qwen 32B
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/nbeerbower%2FQwen2.5-32B-abliterated-LORA"
Response includes
  • classification m5
  • files 4
  • benchmarks 16 entries
  • author_summary 27 models
  • readme_text full
Try next
GET/models?author=nbeerbower
All 27 models by nbeerbower
 GET/models?family=qwen&method=m5
Sibling qwen models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
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
How we label → About M5 →
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 · 30-day
0
Likes
2
Model age
20mo ago
created 2025-01-19
Downloads over time
Now0→from0↑0%
00110 on Jan 15, 20250 on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 15, 2025 → Oct 11 · 130 snapshots · spans 634 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 0.6076015047347256 OpenLLM-v2
IFEval instruct 0.8633093525179856 OpenLLM-v2
IFEval-Prompt 0.8059149722735675 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.566655585106383 OpenLLM-v2
Entertainment 1.2 UGI
Hazardous 1.8 UGI
Natural Intelligence 22.49 UGI
Political lean -17.5% UGI
Sensitive-Info 18.18 UGI
SocPol 2.6 UGI
UGI 22.12 UGI
Willingness (10) 3 UGI
W10-Adherence 1 UGI
W10-Direct 5 UGI
Writing 34.21 UGI

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/Qwen2.5-32B-Instruct this lineage
nbeerbower/Qwen2.5-32B-abliterated-LORA

Metadata

License
apache-2.0
Languages
zho eng fra spa por deu ita rus jpn kor vie tha ara
Tags
transformers safetensors mergekit peft zho eng fra spa por deu ita rus

Related

Other by nbeerbower
Huihui-Qwen3.5-27B-abliterated-Athanorlite-ORPO-v2-GGUF 191 llama-3-spicy-abliterated-stella-8B 46 EVA-abliterated-Qwen2.5-7B 46 Huihui-Qwen3.5-9B-abliterated-Grimoire-SimPO 46 Qwen3-8B-abliterated-TIES 45
Same base model
huihui-ai/Qwen2.5-32B-Instruct-abliterated 5K zetasepic/Qwen2.5-32B-Instruct-abliterated-v2-GGUF 2K zetasepic/Qwen2.5-32B-Instruct-abliterated-v2 119 zetasepic/Qwen2.5-32B-Instruct-abliterated-v2-4.65bpw-exl2 20 async0x42/Qwen2.5-32B-Instruct-abliterated-exl2_4.65bpw 20
Total size
1.04 GB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-28 01:07
Source huggingface.co/nbeerbower/Qwen2.5-32B-abliterated-LORA ↗ Base model Qwen/Qwen2.5-32B-Instruct ↗

Files by quantization

Auxiliary files 4 files 1.04 GB
adapter_model.safetensors 1.04 GB f9f9e931 download
.gitattributes 1.48 KB a6344aac download
README.md 909 B 2c256967 download
adapter_config.json 777 B 8bb0eddd download

README current version from Hugging Face

base_model:

  • Qwen/Qwen2.5-32B-Instruct
  • huihui-ai/Qwen2.5-32B-Instruct-abliterated
    library_name: transformers
    tags:
  • mergekit
  • peft
    license: apache-2.0
    language:
  • zho
  • eng
  • fra
  • spa
  • por
  • deu
  • ita
  • rus
  • jpn
  • kor
  • vie
  • tha
  • ara

Qwen2.5-32B-abliterated-LORA

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from huihui-ai/Qwen2.5-32B-Instruct-abliterated and uses Qwen/Qwen2.5-32B-Instruct as a base.

Parameters

The following command was used to extract this LoRA adapter:

mergekit-extract-lora huihui-ai/Qwen2.5-32B-Instruct-abliterated Qwen/Qwen2.5-32B-Instruct OUTPUT_PATH --rank=64

README history 4 versions

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

  1. 2025-04-28Improve language tag (#1)20f667e871 B
    Loading...
  2. 2025-01-21Update README.mdd6ce2b8783 B
    Loading...
  3. 2025-01-20Update README.md52dfaca765 B
    Loading...
  4. 2025-01-19Upload folder using huggingface_hub3e7e248760 B
    Loading...

Discussions 1 thread

  1. 2025-04-28PRImprove language tagmerged1 💬#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