huihui-ai
Huihui-gpt-oss-20b-BF16-abliterated
20.9B parameters · mixture-of-experts · Instruct · Huihui family
Lineage
Abliterated- Upstream
- gpt-oss-20b-BF16
- Modified by
- huihui-ai
- Method
- refusal-direction ablation — card points at Sumandora/remove-re…
- Canonical modified weights
- available upstream (high-precision weights published)
Method (as documented): refusal-direction ablation — card points at Sumandora/remove-refusals-with-transformers Method parameters: undocumented — no direction index, no layer range, no scale Modifier: huihui-ai (abliteration). Unsloth performed the BF16 conversion beforehand. Parent lineage: openai/gpt-oss-20b (natively MXFP4) -> unsloth/gpt-oss-20b-BF16 (third-party BF16 upcast/dequant, a numerical conversion not a retrain) -> huihui-ai abliteration. TWO links, and the first is a repack by a different party. Notes and caveats: - base_model_import_note: imported during this run - source_precision_caveat: The 'BF16' in the name does NOT mean huihui-ai produced BF16 from training — it inherits BF16 from Unsloth's upcast of an MXFP4 original. Genuine BF16 source weights FOR THIS ABLITERATION, but not a BF16 original relative to OpenAI's release. - repo_format_detail: safetensors 9 shards + a GGUF/ subdirectory containing ggml-model-f16.gguf, ggml-model-q8_0.gguf, ggml-model-Q4_K_M.gguf, ggml-model-Q3_K_M.gguf - collapse_evidence: DavidAU repo declares base_model: huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated in its metadata. Confirmed. - repo_id_correction: The source document's ID for candidate 63 lacks the trailing '-gguf'. The bare form returns 401. Canonical spelling is DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf. - evaluation_note: NONE — no refusal rate, no KL, no capability numbers. Card is warnings and usage code only. Source: refusal-modified-acquisition-manifest.json v1.0.0 (research snapshot 2026-09-20), candidate 60.
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 boardRecommended download
Which version should I download?
Set your rig so we can size a quant to your hardware and show which quants fit.
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
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
- Revision pin
-
b73ec897fe872d5e3fea830d516520537decdde6 - Manifest
- None
License
- Name
- apache-2.0
- Commercial use
- yes
- Access
- Open
File hashes (SHA-256)
No file hashes recorded yet.
Explore further
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.
Performance reports
Real-world throughput reported by the community (and scraped sources).
Community
Reviews, sampler presets and community runtime reports. Be the first to contribute.
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.
Log in to report whether a quant loads in your runtime.
No community reports yet.