← back to catalog · registered 2026-09-12 15:55

KidIkaros/abliterated-minicpm5-2b-lora-finetuned

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
18
Likes
0
Model age
today
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
peft safetensors lora transformers abliterated fine-tuning uncensored text-generation base_model:openbmb/MiniCPM5-2B base_model:adapter:openbmb/MiniCPM5-2B license:apache-2.0 region:us

Related

Total size
95.9 MB
Files
4
Quantizations
1
Registered
2026-09-12 15:55
Last updated on HF
2026-09-12 18:15

Files by quantization

Auxiliary files 4 files 95.9 MB
adapter_model.safetensors 95.9 MB 28a5b2f7 download
README.md 1.82 KB de47d52b download
.gitattributes 1.48 KB a6344aac download
adapter_config.json 1.14 KB 8d0f4515 download

README current version from Hugging Face


base_model: openbmb/MiniCPM5-2B
library_name: peft
license: apache-2.0
pipeline_tag: text-generation
tags:

  • lora
  • transformers
  • abliterated
  • fine-tuning
  • uncensored

LoRA-Fine-Tuned Abliterated MiniCPM5-2B

A LoRA adapter that fine-tunes an abliterated (refusal-removed) MiniCPM5-2B model to improve response quality while maintaining refusal-free behavior.

Model Details

  • Base model: openbmb/MiniCPM5-2B (abliterated)
  • Adapter type: LoRA (r=16, alpha=32, dropout=0.1)
  • Trainable params: 25.1M (1% of 2.5B total)
  • Training steps: 2000
  • Dataset: 5000 high-quality non-refusal training samples
  • Precision: FP16
  • GPU: AMD RX 9060 XT (ROCm 7.2)

Training

  • Dataset: Curated non-refusal conversational + coding data (5000 samples)
  • LR: 3e-4 with cosine annealing, 200 warmup steps
  • Gradient accumulation: 8 steps (effective batch size 16)
  • Training time: ~85 minutes on RX 9060 XT
  • Final loss: ~0.05 (excellent convergence)

Results

The fine-tuned adapter significantly improves response quality:

Task Before (base ablated) After (LoRA)
Factual QA Didn't answer ✅ "Paris"
Coding Didn't answer ✅ Working code
Math Didn't answer ✅ "2x"
Refusal check Over-thought ✅ Non-refusal

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-2B", torch_dtype="auto")
model = PeftModel.from_pretrained(base, "KidIkaros/abliterated-minicpm5-2b-lora-finetuned")

Notes

This is a LoRA adapter — it requires the abliterated base model to function. The base model weights are not included in this repo.

Contact

README history 2 versions

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

  1. 2026-09-12Upload README.md with huggingface_hub4cabab72.7 KB
    Loading...
  2. 2026-09-12LoRA adapter: abliterated MiniCPM5-2B fine-tuned on non-refusal data (2000 st...06244591.8 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.