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

Volko76/Lucie-7B-Instruct-abliterated-exl3

Volko76 Llama 1.6B
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/Volko76%2FLucie-7B-Instruct-abliterated-exl3"
Response includes
  • classification m1
  • files 10
  • hub_downloads_all_time 92
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Volko76
All 2 models by Volko76
 GET/models?family=llama&method=m1
Sibling llama 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
92
35 last 30d - stable
Likes
0
Model age
18mo ago
created 2025-04-10
Downloads over time
Now121→from2↑5,950%
044891332 on Apr 9, 2025121 on Oct 11121 on Oct 8Apr '25Jul '25Oct '25JanAprJulOct
Apr 9, 2025 → Oct 11 · 118 snapshots · spans 550 days

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.

OpenLLM-France/Lucie-7B-Instruct this lineage
Volko76/Lucie-7B-Instruct-abliterated-exl3↓ 35

Metadata

License
apache-2.0
Languages
fr en
Tags
safetensors llama abliterated uncensored fr en base_model:OpenLLM-France/Lucie-7B-Instruct base_model:quantized:OpenLLM-France/Lucie-7B-Instruct license:apache-2.0 4-bit exl3 region:us

Related

Other by Volko76
NanoChatv2_1x_5090_too_uncensored 0
Total size
3.56 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-10 23:40
Source huggingface.co/Volko76/Lucie-7B-Instruct-abliterated-exl3 ↗ Base model OpenLLM-France/Lucie-7B-Instruct ↗

Files by quantization

Auxiliary files 10 files 3.57 GB
model.safetensors 3.56 GB 615eec8e download
tokenizer.json 4.45 MB ef6704c7 download
quantization_config.json 232 KB 6674debe download
LICENSE.md 12.3 KB 3941e339 download
tokenizer_config.json 2.08 KB 7ea1d4d6 download
.gitattributes 1.48 KB a6344aac download
config.json 1020 B 33180a2e download
README.md 741 B c5ec0904 download
special_tokens_map.json 588 B 6ec4ec47 download
generation_config.json 179 B 0647ff74 download

README current version from Hugging Face

license: apache-2.0
language:

  • fr
  • en
    base_model:
  • OpenLLM-France/Lucie-7B-Instruct
    tags:
  • abliterated
  • uncensored

huihui-ai/Lucie-7B-Instruct-abliterated

This is an uncensored version of OpenLLM-France/Lucie-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

You can use huihui_ai/Lucie-abliterated directly

ollama run huihui_ai/Lucie-abliterated

README history 1 version

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

  1. 2025-04-10Upload folder using huggingface_hube03e10e741 B
    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.

Get the app Browse the catalog
Open in Abliteration