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

CombinHorizon/huihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES

CombinHorizon Qwen 15B second-order
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/CombinHorizon%2Fhuihui-ai-abliteratedV2-Qwen2.5-14B-Inst-BaseMerge-TIES"
Response includes
  • classification m5
  • files 18
  • benchmarks 16 entries
  • hub_downloads_all_time 378
  • author_summary 4 models
  • readme_text full
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
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.

What is a refusal direction? →
Downloads · lifetime
378
36 last 30d - cooling
Likes
2
Descendants
4
in 4 direct forks
Model age
22mo ago
created 2024-12-07
Downloads over time
Now397→from12↑3,208%
014529143612 on Dec 4, 2024397 on Oct 11Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 4, 2024 → Oct 11 · 136 snapshots · spans 676 days

Benchmarks

Benchmark Score Source
BBH average 0.5638863665845116 OpenLLM-v2
IFEval instruct 0.8633093525179856 OpenLLM-v2
IFEval-Prompt 0.8022181146025879 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.49617686170212766 OpenLLM-v2
Entertainment 1 UGI
Hazardous 1.8 UGI
Natural Intelligence 19.21 UGI
Political lean -10.8% UGI
Sensitive-Info 17.01 UGI
SocPol 2.5 UGI
UGI 38.84 UGI
Willingness (10) 8.2 UGI
W10-Adherence 8.5 UGI
W10-Direct 8 UGI
Writing 29.12 UGI

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.

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen2 text-generation mergekit merge qwen2.5 TIES conversational en arxiv:2306.01708 arxiv:2407.10671

Related

Total size
27.5 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-12-07 05:13

Files by quantization

Auxiliary files 18 files 27.5 GB
model-00002-of-00006.safetensors 4.61 GB 9f27cefa download
model-00003-of-00006.safetensors 4.61 GB d322e269 download
model-00004-of-00006.safetensors 4.61 GB 6bf505d9 download
model-00005-of-00006.safetensors 4.61 GB 248aca63 download
model-00001-of-00006.safetensors 4.57 GB 4ed08822 download
model-00006-of-00006.safetensors 4.48 GB 60954391 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 44.1 KB f54a2fb9 download
tokenizer_config.json 7.06 KB 40669356 download
README.md 2.39 KB bdf699ab download
.gitattributes 1.53 KB 52373fe2 download
config.json 725 B 4e1353b7 download
special_tokens_map.json 616 B 17305b36 download
added_tokens.json 605 B 482ced46 download
generation_config.json 243 B f237e177 download
mergekit_config.yml 242 B 5b208b97 download

README current version from Hugging Face


base_model:

  • huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
  • Qwen/Qwen2.5-14B
    library_name: transformers
    tags:
  • mergekit
  • merge
  • qwen2.5
  • TIES
    license: apache-2.0
    language:
  • en
    pipeline_tag: text-generation

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen2.5-14B as a base.

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/Qwen2.5-14B-Instruct-abliterated-v2
   parameters:
     weight: 1
     density: 1
merge_method: ties
base_model: Qwen/Qwen2.5-14B
parameters:
 weight: 1
 density: 1
 normalize: true
 int8_mask: true
dtype: bfloat16

Citations

The merge is based on the technique posted here.

@misc{qwen2.5,
    title = {Qwen2.5: A Party of Foundation Models},
    url = {https://qwenlm.github.io/blog/qwen2.5/},
    author = {Qwen Team},
    month = {September},
    year = {2024}
}

@article{qwen2,
      title={Qwen2 Technical Report}, 
      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
      journal={arXiv preprint arXiv:2407.10671},
      year={2024}
}

README history 3 versions

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

  1. 2024-12-07Update README.mdd92237b2.4 KB
    Loading...
  2. 2024-12-07Update README.mddbcba2d2.4 KB
    Loading...
  3. 2024-12-07Upload folder using huggingface_hub1866b65986 B
    Loading...

Discussions 1 thread

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

Open in Abliteration