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

mitkox/gemma-2b-dpo-uncensored-4bit

mitkox Gemma 2.0B
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/mitkox%2Fgemma-2b-dpo-uncensored-4bit"
Response includes
  • classification m-uncensored
  • files 11
  • benchmarks 5 entries
  • hub_downloads_all_time 21,390
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=mitkox
All 2 models by mitkox
 GET/models?family=gemma&method=m-uncensored
Sibling gemma models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
21K
537 last 30d - cooling
Likes
6
Model age
2.6y ago
created 2024-02-22

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
Downloads over time
Now21.6K→from507↑4,158%
07.9K15.8K23.7K507 on Jul 24, 202421.6K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 156 snapshots · spans 809 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 4918 LM-Arena
LM Arena Elo 1011.7405090671136 LM-Arena
Arena-Elo-Lower 1000.3091880949547 LM-Arena
Arena-Elo-Upper 1023.1718300392724 LM-Arena
Arena-Rank 227 LM-Arena

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.

google/gemma-2b-it this lineage
mitkox/gemma-2b-dpo-uncensored-4bit↓ 537

Metadata

License
cc-by-nc-4.0
Languages
en
Tags
transformers safetensors gemma text-generation generated_from_trainer axolotl instruct finetune chatml gpt4 synthetic data distillation

Related

Other by mitkox
Huihui-Qwen3.8-27B-abliterated-Q4_K_M-GGUF 1K
Total size
7.54 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-02-22 09:24
Source huggingface.co/mitkox/gemma-2b-dpo-uncensored-4bit ↗ Base model google/gemma-2b-it ↗

Files by quantization

Auxiliary files 11 files 7.56 GB
model-00001-of-00002.safetensors 4.97 GB 0ec1248c download
model.safetensors 2.01 GB c989b3be download
model-00002-of-00002.safetensors 567 MB b1307c70 download
tokenizer.json 16.7 MB 05e97791 download
tokenizer.model 4.04 MB 6969e640 download
model.safetensors.index.json 28.6 KB 9c56dc8c download
config.json 2.33 KB 81926614 download
tokenizer_config.json 2.10 KB f66eacb3 download
.gitattributes 1.53 KB 52373fe2 download
README.md 643 B 924afab9 download
special_tokens_map.json 636 B 8d6368f7 download

README current version from Hugging Face

language:

  • en
    license: cc-by-nc-4.0
    library_name: transformers
    tags:
  • generated_from_trainer
  • axolotl
  • gemma
  • instruct
  • finetune
  • chatml
  • gpt4
  • synthetic data
  • distillation
  • mlx
    datasets:
  • mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
    base_model: google/gemma-2b-it
    pipeline_tag: text-generation
    model-index:
  • name: gemma-2b-openhermes
    results: []

mitkox/gemma-2b-dpo-uncensored-4bit

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mitkox/gemma-2b-dpo-uncensored-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

README history 2 versions

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

  1. 2024-02-22Update README.mdc9528fa643 B
    Loading...
  2. 2024-02-22Upload folder using huggingface_hubbbb33f2840 B
    Loading...

Discussions 3 threads

  1. 2024-03-20Does anyone know how to fine tune this model?open1 💬#3
    Loading...
  2. 2024-02-22Multiple models included (should only be the single 4-bit safetensor file)closed1 💬#2
    Loading...
  3. 2024-02-22please convert to ggufopen3 💬#1
    Loading...

Continue on Hugging Face →

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