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

usermma/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated

usermma Llama 1.1B
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%2FMiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated"
Response includes
  • classification m1
  • files 13
  • hub_downloads_all_time 49
  • author_summary 77 models
  • readme_text full
Try next
GET/models?author=usermma
All 77 models by usermma
 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
49
9 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
3mo ago
created 2026-07-10
Downloads over time
Now56→from26↑115%
2536485926 on Jul 1556 on Oct 1156 on Oct 9JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 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.

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking this lineage
usermma/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated↓ 9 2 forks
mradermacher/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated-i1-GGUF↓ 1,037
mradermacher/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated-GGUF↓ 435

Metadata

Tags
safetensors llama obliteratus abliteration uncensored obliterate en base_model:GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking base_model:finetune:GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking 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
Total size
2.01 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-10 08:20
Source huggingface.co/usermma/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated ↗ Base model GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking ↗

Files by quantization

Auxiliary files 13 files 2.02 GB
model-00001-of-00002.safetensors 1.64 GB 65432d67 download
model-00002-of-00002.safetensors 383 MB 82ccc9b6 download
tokenizer.json 9.44 MB 1df83b86 download
model.safetensors.index.json 17.6 KB ce9ed7d5 download
chat_template.jinja 8.85 KB cb2934c4 download
abliteration_metadata.json 1.63 KB aa066803 download
.gitattributes 1.48 KB a6344aac download
README.md 1.19 KB c3583353 download
config.json 748 B c17d5f9b download
tokenizer_config.json 733 B 69ad8657 download
obliteratus_session.json 319 B 2c3bcd17 download
generation_config.json 234 B cedce495 download
.quick_checkpoint 18.0 B 27769b5b download

README current version from Hugging Face

language: en
tags:

  • obliteratus
  • abliteration
  • uncensored
  • obliterate
    base_model: GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking

MiniCPM5-1B-Claude-Opus-Fable5-Thinking-OBLITERATED

This model was abliterated using the failspy method via
OBLITERATUS.

Detail Value
Base model GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking
Method failspy
Source obliterate

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("MiniCPM5-1B-Claude-Opus-Fable5-Thinking-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("MiniCPM5-1B-Claude-Opus-Fable5-Thinking-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. 2026-07-10OBLITERATUS: failspy on GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking062d0991.2 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.

Get the app Browse the catalog
Open in Abliteration