← back to catalog · registered 2026-11-15 16:03

usermma/tinybrainbot-53m-a9m-hybrid-instruct-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/usermma%2Ftinybrainbot-53m-a9m-hybrid-instruct-abliterated"
Response includes
  • classification m1
  • files 11
  • author_summary 79 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 · 30-day
97
Likes
0
Descendants
1
in 1 direct fork
Model age
6d ago
created 2026-11-15
Downloads over time
Now 97 → from 0 ↑ 0%
03671107 0 on Nov 15 97 on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 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.

Variants by this author 2 formats · 472 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
safetensors lfm2_moe obliteratus abliteration uncensored obliterate text-generation conversational en base_model:nkthebass/tinybrainbot-53m-a9m-hybrid-instruct base_model:finetune:nkthebass/tinybrainbot-53m-a9m-hybrid-instruct license:apache-2.0

Related

Total size
102 MB
Files
11
Quantizations
1
Registered
2026-11-15 16:03
Last updated on HF
2026-11-16 05:45

Files by quantization

Auxiliary files 11 files 105 MB
model.safetensors 102 MB ec10b9f2 download
tokenizer.json 3.31 MB a9c85a7e download
chat_template.jinja 6.92 KB 47d02648 download
abliteration_metadata.json 1.62 KB 3d5863ab download
.gitattributes 1.48 KB a6344aac download
README.md 1.18 KB 20f0bd92 download
config.json 1023 B 3f401b4c download
tokenizer_config.json 485 B bd83e6dc download
obliteratus_session.json 306 B 3eaebd52 download
generation_config.json 231 B 92876cb4 download
.quick_checkpoint 18.0 B 27769b5b download

README current version from Hugging Face


language: en
tags:

  • obliteratus
  • abliteration
  • uncensored
  • obliterate
    base_model: nkthebass/tinybrainbot-53m-a9m-hybrid-instruct

tinybrainbot-53m-a9m-hybrid-instruct-abliterated

This model was abliterated using the advanced method via
OBLITERATUS.

Detail Value
Base model nkthebass/tinybrainbot-53m-a9m-hybrid-instruct
Method advanced
Source obliterate

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("tinybrainbot-53m-a9m-hybrid-instruct-abliterated")
tokenizer = AutoTokenizer.from_pretrained("tinybrainbot-53m-a9m-hybrid-instruct-abliterated")

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 4 versions

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

  1. 2026-11-16 Update README.md 2da1ff8 1.2 KB
    Loading...
  2. 2026-11-15 Update README.md 944ae3f 1.2 KB
    Loading...
  3. 2026-11-15 Update README.md 9767b06 1.2 KB
    Loading...
  4. 2026-11-15 OBLITERATUS: advanced on nkthebass/tinybrainbot-53m-a9m-hybrid-instruct c370486 1.2 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