CUSTOM
CLANKERS.
← Browse all models

ArliAI / Model details

gpt-oss-20b-Derestricted

ArliAI/gpt-oss-20b-Derestricted

abliterateduncensoredfine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

About this model

ArliAI's refusal-modified derivative of gpt-oss-20b. The creator describes norm-preserving biprojected abliteration and warns that the model may still try to suppress some requests. This is a BF16 safetensors release, not the original base model's MXFP4 weight package; the base card's 16GB memory claim does not establish this derivative's requirements. Refusal behavior and claims about retained reasoning have not been tested here.

Description sources

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model
openai/gpt-oss-20b
Parameters
20.9148B
Main repository formats
safetensors
License tag
apache-2.0
Languages
Unknown
Last updated
2025-11-28 · 10:38:22.000 UTC

Community reviews & tips

Source-linked paraphrases of sampled community sources, not independently tested by this directory.

Sample window: to · 1 unique source link. This is a selected sample, not all community discussions.

Small sample: source links are not a count of independent reviewers or evidence of consensus.

Sources checked:

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

  • abliteratedsource tag: abliterated
  • uncensoredsource tag: uncensored
  • fine-tunedsource tag: base_model:finetune:openai/gpt-oss-20b

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

  • gpt-oss: Base model: openai/gpt-oss-20b

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Download sources

ModelScope distribution ↗
  • Distribution checked: ModelScope · 2026-10-24 · 03:14:44 UTC

Distribution links are not independent reviews or runtime compatibility guarantees. Check each source’s exact files and instructions.

Refusal profile

Refused 0 of 42 prompts (0.0%)

We asked this model 120 benign but risky-looking prompts across ten topics and counted how often it refused, hedged or answered. Lower means it answered more often; it says nothing about answer quality.

  • Persuasion & deception0 refused · 0 partial · 5 complied
  • Harassment & confrontation0 refused · 0 partial · 3 complied
  • Risky activities0 refused · 0 partial · 4 complied
  • Offensive & controversial speech0 refused · 0 partial · 7 complied
  • Legal grey areas0 refused · 0 partial · 3 complied
  • Privacy & personal data0 refused · 0 partial · 6 complied
  • Self-harm & mental health topics0 refused · 0 partial · 4 complied
  • Sexual & adult topics0 refused · 0 partial · 4 complied
  • Ethically grey requests0 refused · 0 partial · 5 complied
  • Violence & conflict0 refused · 0 partial · 1 complied

Capability check: 14 of 15 passed. Fifteen simple tasks with known answers, so a broken model cannot score well by refusing nothing.

Unclear answers: 78 (not counted). An answer is unclear when the two checker models disagree or the output was empty or garbled.

Too many unclear answers to rank: this model appears on the Refusal Index but is not placed in the ranking.

Measured 2026-10-25 · Q4_K_M via MaziyarPanahi/gpt-oss-20b-Derestricted-GGUF ↗ · llama.cpp · prompt set v1

How we measure · The prompts

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/arliai-gpt-oss-20b-derestricted/)

HTML

<a href="https://customclankers.com/models/arliai-gpt-oss-20b-derestricted/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Linked in the model card

GitHub repositories the original model card links to.

  • openai/harmony ↗

    Repo’s own description: Renderer for the harmony response format to be used with gpt-oss

    ★ 4,531 · Last updated 2026-04-08 · License: Apache-2.0

  • openai/gpt-oss ↗

    Repo’s own description: gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

    ★ 20,492 · Last updated 2026-10-12 · License: Apache-2.0

Tools to customize it further

Remove more refusals

  • Heretic ↗ ★ 36,421

    Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.

  • OBLITERATUS ↗ ★ 8,946

    A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.

Fine-tune it on your own data

  • Unsloth ↗ ★ 78,528

    A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.

  • LlamaFactory ↗ ★ 75,713

    Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,260

    Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

  • MLX LM ↗ ★ 7,467

    Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.

Merge it with another model

  • mergekit ↗ ★ 7,414

    Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.

Learn the techniques

  • LLM Course ↗ ★ 84,667

    A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads
252
Likes
99
Metadata checked
2026-10-25 · 05:05:23 UTC
First seen in index
2026-10-22 · 22:59:23 UTC
Source revision
9eff9a0e1fbe9bd16262018a3bb8ae9195fa0979

Source-card excerpt

Source model card excerpt: Arli AI gpt-oss-20b-Derestricted After the initial success of GLM-4.5-Air-Derestricted, we thought it would be interesting to try and Derestrict one of the most famously

From ArliAI/gpt-oss-20b-Derestricted. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗