p-e-w

gpt-oss-20b-heretic

Name: gpt-oss-20b-heretic
Author: p-e-w

20.9B parameters · mixture-of-experts · Instruct · gpt family

Mixture-of-experts — what it means for memory & speed → Long context — how it uses memory →

apache-2.0 source matched revision pinned

Lineage

Abliterated

Upstream: gpt-oss-20b
Modified by: p-e-w
Method: heretic
Canonical modified weights: available upstream (high-precision weights published)

Method (as documented): heretic Method version: Heretic v1.0.0 Method parameters: direction index 16.66; per-component ablation weight thresholds reported in range 0.64-1.44 across attn/MLP projections. APPROXIMATE — exact max/min block not captured verbatim; re-read card before recording. Modifier: p-e-w Notes and caveats: - gguf_note: The most-adopted GGUF (DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf, 25257 dl/30d, 186 likes) is a re-tuned NEO-Imatrix variant, NOT a faithful quant. Prefer bartowski (3746 dl) for a clean conversion. Reported evaluations with non-numeric values (kept verbatim here; benchmarks.score is NOT NULL so no row was created): - {"metric":"refusals","value":"58/100","baseline":"100/100","evaluator":"p-e-w","is_author_reported":true,"evaluation_type":"refusal"} Source: refusal-modified-acquisition-manifest.json v1.0.0 (research snapshot 2026-09-20), candidate 59.

Nothing to download yet — request it on the board

We catalog this model, but no build is staged here yet. Add it to the request board so we know there is demand to mirror it.

Request this model on the board

Which version should I download?

Set your rig so we can size a quant to your hardware and show which quants fit.

Set your rig

Quantizations

Why these quants? Which quant should I pick? What do these mean?

No quantizations published yet.

Want a different quant? Request it on the board →

Context

Advertised 128k · no independent evidence yet

No independent long-context evidence has been graded for this model yet — the advertised window above is the maintainer's number, not a usable-context claim.

Run it

Quant

Context / KV 8,192 tokens · FP16 set above the quant table

No quant selected.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance: https://huggingface.co/p-e-w/gpt-oss-20b-heretic
Revision pin: 40a07b3c6d681a949db1ace3185050b5a0893093
Manifest: None

License

Name: apache-2.0
Commercial use: yes
Access: Open

How verification works →

File hashes (SHA-256)

No file hashes recorded yet.

Explore further

Also consider

Get an email when a better quant fits your rig.

Set your rig once; we'll alert you when a new or better-fitting build lands.

Set your rig

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Community

Reviews, sampler presets and community runtime reports. Be the first to contribute.

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

No community reports yet.