Bahushruth/Qwen3.6-35B-A3B-abliterated-v4
2 files
trained on 2 datasets 2 in /datasets
↓ 475K
♥ 12
AUTHOR
8 models in the catalog. 489K total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 1 alignment dataset (1.2k downloads).
Bahushruth/Qwen3.6-35B-A3B-abliterated-v4-GGUF
10 quantizations
trained on 1 dataset 1 in /datasets
↓ 13K
♥ 8
Bahushruth/Qwen3.6-27B-abliterated-GGUF
4 quantizations
↓ 393
♥ 4
Bahushruth/GLM-5.2-FP8-abliterated
152 files
trained on 2 datasets 2 in /datasets
↓ 51
♥ 21
Bahushruth/gemma-4-E4B-it-abliterated
1 files
trained on 2 datasets 2 in /datasets
↓ 27
♥ 0
Bahushruth/gemma-4-31B-it-abliterated
2 files
trained on 2 datasets 2 in /datasets
↓ 26
♥ 0
Bahushruth/gemma-4-26B-A4B-it-abliterated
2 files
trained on 2 datasets 2 in /datasets
↓ 23
♥ 0
Bahushruth/gemma-4-E2B-it-abliterated
1 files
trained on 2 datasets 2 in /datasets
↓ 17
♥ 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...
1.2k
7
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...
1.2k
7
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...
1.2k
7