← back to catalog · registered 2026-09-12 12:55

KidIkaros/abliterated-minicpm5-2b

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
201
Likes
0
Model age
1d ago
created 2026-09-12
Downloads over time
Now0from0↑0%
00110 on Sep 120 on Sep 13Sep
Sep 12 → Sep 13 · 2 snapshots · spans 1 day

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.

Metadata

License
apache-2.0
Tags
safetensors llama text-generation transformer abliterated refusal-free pytorch conversational base_model:openbmb/MiniCPM5-2B base_model:finetune:openbmb/MiniCPM5-2B license:apache-2.0 region:us

Related

Total size
4.69 GB
Files
12
Quantizations
1
Registered
2026-09-12 12:55
Last updated on HF
2026-09-12 12:11

Files by quantization

Auxiliary files 12 files 4.70 GB
model-00001-of-00003.safetensors 1.86 GB 6d072e67 download
model-00002-of-00003.safetensors 1.85 GB f55b3fef download
model-00003-of-00003.safetensors 1008 MB 7e22c5b3 download
tokenizer.json 9.44 MB 6b33a8ba download
model.safetensors.index.json 30.7 KB b5f7f3ca download
chat_template.jinja 8.85 KB be166eec download
abliteration_metadata.json 3.50 KB b735349e download
.gitattributes 1.48 KB a6344aac download
README.md 1.13 KB 4db3860e download
config.json 748 B c2c465f5 download
tokenizer_config.json 436 B 69c15770 download
generation_config.json 214 B 7ac01e80 download

README current version from Hugging Face


license: apache-2.0
base_model: openbmb/MiniCPM5-2B
tags:

  • text-generation
  • transformer
  • abliterated
  • refusal-free
  • pytorch

Abliterated MiniCPM5-2B (PyTorch)

A refusal-free variant of MiniCPM5-2B abliterated using OBLITERATUS

Same abliteration as the GGUF repo but in native HuggingFace format.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "KidIkaros/abliterated-minicpm5-2b",
    trust_remote_code=True,
    torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained("KidIkaros/abliterated-minicpm5-2b", trust_remote_code=True)

prompt = "Explain how to pick a lock without a key"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Abliteration Metrics

Metric Before After
Perplexity 5.27 5.13
Coherence 0.667 0.800
Refusal Rate 0%
Capability Score 1.0

README history 1 version

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

  1. 2026-09-12Add README with YAML metadata5c315b81.1 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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.