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

usermma/Holo-3.1-4B-abliterated-rdo

usermma 4.8B
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/usermma%2FHolo-3.1-4B-abliterated-rdo"
Response includes
  • classification m1
  • files 16
  • hub_downloads_all_time 39
  • author_summary 77 models
  • readme_text full
Try next
GET/models?author=usermma
All 77 models by usermma
 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
39
10 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
4mo ago
created 2026-06-05
Downloads over time
Now44→from21↑110%
2029374621 on Jun 1044 on Oct 1144 on Oct 8JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 days

Genealogy 2 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.

Hcompany/Holo-3.1-4B this lineage
usermma/Holo-3.1-4B-abliterated-rdo↓ 10 2 forks
mradermacher/Holo-3.1-4B-abliterated-rdo-i1-GGUF↓ 1,238
mradermacher/Holo-3.1-4B-abliterated-rdo-GGUF↓ 565

Metadata

Tags
safetensors qwen3_5_text obliteratus abliteration uncensored obliterate en base_model:Hcompany/Holo-3.1-4B base_model:finetune:Hcompany/Holo-3.1-4B region:us

Related

Other by usermma
Huihui-MiniCPM5-1B-abliterated-mlx-2Bit 279 Huihui-LFM2.5-8B-A1B-abliterated-mlx-2Bit 166 Huihui-LFM2.5-8B-A1B-abliterated-mlx-fp16 164 Qwythos-9B-v2-Heretic-Abliterated 133 DeepHat-V1-7B-Heretic-Abliterated-mlx-8Bit 126
Same base model
noahoksuz/Holo-3.1-4B-uncensored-heretic 637
Total size
9.02 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-05 09:12
Source huggingface.co/usermma/Holo-3.1-4B-abliterated-rdo ↗ Base model Hcompany/Holo-3.1-4B ↗

Files by quantization

Auxiliary files 16 files 9.04 GB
model-00001-of-00005.safetensors 1.86 GB 1d499eda download
model-00003-of-00005.safetensors 1.85 GB f912a1ba download
model-00002-of-00005.safetensors 1.84 GB 22200f9b download
model-00004-of-00005.safetensors 1.83 GB 556fcd21 download
model-00005-of-00005.safetensors 1.64 GB 1cc0a033 download
tokenizer.json 19.1 MB 0f069a09 download
model.safetensors.index.json 34.8 KB 191fbb83 download
chat_template.jinja 7.57 KB a585dec8 download
config.json 1.89 KB 0b0f2298 download
abliteration_metadata.json 1.60 KB 35e7239d download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.26 KB 5db46b93 download
README.md 1.05 KB e025bc65 download
generation_config.json 233 B 42341123 download
obliteratus_session.json 219 B fcf8b591 download
.quick_checkpoint 18.0 B 27769b5b download

README current version from Hugging Face

language: en
tags:

  • obliteratus
  • abliteration
  • uncensored
  • obliterate
    base_model: Hcompany/Holo-3.1-4B

Holo-3.1-4B-OBLITERATED

This model was abliterated using the rdo method via
OBLITERATUS.

Detail Value
Base model Hcompany/Holo-3.1-4B
Method rdo
Source obliterate

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Holo-3.1-4B-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("Holo-3.1-4B-OBLITERATED")

prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

About OBLITERATUS

OBLITERATUS is an open-source tool for removing refusal behavior from language
models via activation engineering (abliteration). Learn more at
github.com/elder-plinius/OBLITERATUS.

README history 1 version

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

  1. 2026-06-05OBLITERATUS: rdo on Hcompany/Holo-3.1-4Bde9e27d1 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.

Get the app Browse the catalog
Open in Abliteration