Get the app
← back to catalog · registered 2026-09-24 13:57

OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated

OliviaRossi 9B 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/OliviaRossi%2FMiMo-Ornith-9B-AGSI-Abliterated"
Response includes
  • classification m1
  • files 10
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=OliviaRossi
All 3 models by OliviaRossi
 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 · 30-day
0
Likes
1
Model age
today
created 2026-09-23

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.

OliviaRossi/MiMo-Ornith-9B-AGSI this lineage
OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated

Metadata

License
mit
Languages
en zh
Tags
safetensors qwen3_5 abliterated abliterix uncensored reasoning agentic text-generation conversational en zh base_model:OliviaRossi/MiMo-Ornith-9B-AGSI

Related

Other by OliviaRossi
gemma-4-19B-A4B-it-INSTRUCT-Heretic-Uncensored-Q2_K-GGUF 61 Qwen3.8-27B-Uncensored-Aggressive-no-mtp 0
Total size
17.5 GB
Files
10
Quantizations
1
Registered
2026-09-24 13:57
Last updated on HF
2026-09-24 12:50
Source huggingface.co/OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated ↗ Base model OliviaRossi/MiMo-Ornith-9B-AGSI ↗

Files by quantization

Auxiliary files 10 files 17.5 GB
model.safetensors 17.5 GB afe98cfe download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
tokenizer_config.json 17.2 KB ff6581d0 download
chat_template.jinja 9.88 KB ccca0575 download
config.json 2.84 KB 3c302c44 download
.gitattributes 1.53 KB 52373fe2 download
README.md 320 B 5849d282 download
generation_config.json 126 B 06320848 download

README current version from Hugging Face

license: mit
language:

  • en
  • zh
    base_model:
  • OliviaRossi/MiMo-Ornith-9B-AGSI
    tags:
  • abliterated
  • abliterix
  • uncensored
  • reasoning
  • qwen3_5
  • agentic
    pipeline_tag: text-generation

MiMo-Ornith-9B-AGSI-Abliterated

Abliterated using Abliterix. Full reasoning template and tool call architecture preserved.

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 app" button that hands off directly to a local runtime of your choice - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog