← back to catalog · registered 2026-11-17 22:04

bowtiedrahman/voltron-1-mini-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/bowtiedrahman%2Fvoltron-1-mini-abliterated"
Response includes
  • classification m8
  • files 15
  • author_summary 5 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
481
Likes
1
Descendants
1
in 1 direct fork
Model age
4d ago
created 2026-11-17
Downloads over time
Now 481 → from 0 ↑ 0%
0176353529 0 on Nov 17 481 on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 days

Genealogy 1 direct fork

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
other
Quantizations
Q4_K
Tags
transformers safetensors gguf lfm3 text-generation liquid abliterated uncensored heretic llama.cpp conversational custom_code

Related

Total size
5.96 GB
Files
15
Quantizations
2
Registered
2026-11-17 22:04
Last updated on HF
2026-11-21 07:14

Files by quantization

Q4_K 1 file 1.02 GB
voltron-1-mini-abliterated-Q4_K_M.gguf 1.02 GB 9dc34649 download
Auxiliary files 14 files 4.96 GB
model.safetensors 3.22 GB 76fa4397 download
voltron-1-mini-abliterated-q8_0.gguf 1.72 GB c4759285 download
tokenizer.json 17.1 MB 8f7ed418 download
modeling_lfm3.py 41.4 KB 0ccffc7e download
chat_template.jinja 11.8 KB d0747b8b download
LICENSE 10.3 KB 25e731c6 download
lfm3_conv.py 8.33 KB a1b67afd download
configuration_lfm3.py 5.97 KB a3cc0e72 download
tokenizer_config.json 1.82 KB aed9ef7d download
.gitattributes 1.68 KB c7872637 download
config.json 1.53 KB 8cff7b87 download
README.md 1.44 KB 8ceb0616 download
heretic_trial.json 584 B 87d0c1cb download
generation_config.json 328 B 0df27460 download

README current version from Hugging Face


license: other
license_name: lfm-open-license-v1.0
license_link: LICENSE
base_model: Akahsizrr/voltron-1-mini
library_name: transformers
pipeline_tag: text-generation
tags:

  • liquid
  • lfm3
  • abliterated
  • heretic
  • gguf

voltron-1-mini-abliterated

Modified weights. This is Akahsizrr/voltron-1-mini
with its refusal behavior reduced by directional ablation (abliteration) using
Heretic v1.4.0. Modification notice per LFM Open License v1.0 section 4(b):
the model weights were changed. Liquid AI does not endorse this build.

Method

Same recipe as bowtiedrahman/LFM3-1.7B-abliterated:
residual means over 400 harmless and 400 harmful prompts, per-layer refusal directions with
orthogonalize_direction, and ablation of attention output, conv output and MLP down projections with
the trial-74 weight schedule. voltron-1-mini is a fine-tune of LFM3-1.7B, so the schedule transfers.

Files

model.safetensors merged bf16 weights. Custom code files for trust_remote_code. GGUF quantizations
are not included yet and can be built the same way as the LFM3 ones.

Limits

Abliteration removes refusal behavior, not capability limits, and not all of it: the base recipe left
11 refusals per 100 on a held-out harmful set. Expect uneven removal on prompts unlike the training
distribution of the ablation data.

README history 2 versions

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

  1. 2026-11-21 Upload README.md with huggingface_hub d70f014 3.9 KB
    Loading...
  2. 2026-11-17 model card with method and license notice 5cd598a 1.4 KB
    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