spinochenza/Huihui-Ornith-1.5-35B-A3B-abliterated
16 files
↓ 168
♥ 1
AUTHOR
17 models in the catalog. 488 total downloads. First seen 2026-08-22, last activity 2026-08-30. Also publishes 2 alignment datasets (243 downloads).
spinochenza/Huihui-Agents-A1-abliterated
14 files
↓ 34
♥ 0
spinochenza/Minimax-M3-abliterated-clean
59 files
↓ 32
♥ 0
spinochenza/Huihui-Qwen3.8-27B-abliterated
18 files
↓ 30
♥ 0
spinochenza/Huihui-Qwen3-Coder-Next-abliterated
32 files
↓ 26
♥ 0
spinochenza/Qwen3.6-35B-A3B-uncensored-heretic
2 files
↓ 24
♥ 0
spinochenza/Huihui-Kimi-Linear-REAP-35B-A3B-Instruct-abliterated
15 files
↓ 20
♥ 1
spinochenza/Qwen3.5-122B-A10B-abliterated
39 files
↓ 20
♥ 0
spinochenza/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
2 files
↓ 20
♥ 0
spinochenza/MiniMax-M2.7-BF16-ultra-uncensored-heretic
92 files
↓ 19
♥ 0
spinochenza/Nex-N2-mini-ultra-uncensored-heretic
2 files
↓ 17
♥ 1
spinochenza/Qwen3.6-27B-uncensored-heretic-v2
2 files
↓ 17
♥ 0
spinochenza/Huihui-MiroThinker-v1.5-30B-abliterated
13 files
↓ 15
♥ 0
spinochenza/Huihui-Qwen3.6-35B-A3B-abliterated
26 files
↓ 13
♥ 0
spinochenza/Huihui-Qwen3.6-27B-abliterated
15 files
↓ 12
♥ 0
spinochenza/Huihui-Nex-N2-mini-abliterated
16 files
↓ 12
♥ 0
spinochenza/Ornith-1.0-35B-uncensored-heretic
2 files
↓ 9
♥ 0
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
abliteration-harmful-enriched 0 0
abliteration-harmful-enriched
Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33...
159
-
cyberstrike-sft-120k 0 0
CyberStrike SFT 120K
The largest open-source offensive cybersecurity SFT dataset
121,422 expert-level red team instruction-r...
84
1
Dataset
Stage
Downloads
Likes
cyberstrike-sft-120k 0 0
CyberStrike SFT 120K
The largest open-source offensive cybersecurity SFT dataset
121,422 expert-level red team instruction-r...
84
1
abliteration-harmful-enriched 0 0
abliteration-harmful-enriched
Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33...
159
-
Dataset
Stage
Downloads
Likes
cyberstrike-sft-120k 0 0
CyberStrike SFT 120K
The largest open-source offensive cybersecurity SFT dataset
121,422 expert-level red team instruction-r...
84
1
abliteration-harmful-enriched 0 0
abliteration-harmful-enriched
Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33...
159
-