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

Local-Novel-LLM-project/Vecteus-v1-abliterated

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/Local-Novel-LLM-project%2FVecteus-v1-abliterated"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 48
  • author_summary 1 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
48
5 last 30d - stable
Likes
13
Descendants
3
in 3 direct forks
Model age
23mo ago
created 2024-11-12
Downloads over time
Now50→from29↑72%
028757386029 on Dec 18, 202450 on Oct 11782 on Dec 10, 2025Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 18, 2024 → Oct 11 · 134 snapshots · spans 662 days

Genealogy 3 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
ja
Tags
transformers safetensors mistral text-generation conversational ja base_model:mistralai/Mistral-7B-v0.1 base_model:finetune:mistralai/Mistral-7B-v0.1 license:apache-2.0 text-generation-inference endpoints_compatible region:us
Total size
13.5 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-12-17 07:55

Files by quantization

Auxiliary files 11 files 13.5 GB
model-00002-of-00003.safetensors 4.66 GB ******** download
model-00001-of-00003.safetensors 4.60 GB ******** download
model-00003-of-00003.safetensors 4.23 GB ******** download
tokenizer.model 482 KB ******** download
model.safetensors.index.json 23.4 KB b349bc0c download
tokenizer_config.json 1.49 KB dc234c93 download
.gitattributes 1.48 KB a6344aac download
README.md 1.47 KB fc6379ef download
config.json 669 B 22ab7fca download
special_tokens_map.json 414 B 451134b2 download
generation_config.json 111 B 378a6350 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
language:

  • ja
    base_model:
  • mistralai/Mistral-7B-v0.1
    pipeline_tag: text-generation

概要

vecteusは、高性能な日本語大規模言語モデルです。小説のドメインに特化し、かつ自然な日本語の生成や理解において優れた性能を発揮します。

当リポジトリは、vecteus v1をベースとした、フィルター(検閲機能)を削除したabliterated版を提供しています。元モデルに存在した出力に対する制約を取り払うことで、より自由度の高いテキスト生成を可能にしています。
ただし、この変更により、生成されるテキストの内容については一切の責任を負いません。

  • 高度な日本語自然言語理解: vecteusは、日本語の文法や意味構造を深く理解し、複雑な日本語の文章を生成することができます。
  • 多様なタスクへの対応: テキスト生成、質問応答、要約、翻訳など、幅広い自然言語処理タスクに対応しています。
  • 検閲フィルターの削除 (abliterated-vecteus): 初代vecteusに存在した出力フィルターを削除し、より自由なテキスト生成を可能にしました。

参考

https://huggingface.co/blog/mlabonne/abliteration

https://github.com/FailSpy/abliterator

https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction

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