knoveleng/Qwen2.5-3B-Instruct-Uncensored
2 files
↓ 189
♥ 1
AUTHOR
10 models in the catalog. 665 total downloads. First seen 2026-08-22, last activity 2026-08-26. Also publishes 2 alignment datasets (13.1k downloads).
knoveleng/Qwen3.5-4B-Uncensored
1 files
↓ 189
♥ 1
knoveleng/Llama-3.2-3B-Instruct-Uncensored
2 files
↓ 77
♥ 0
knoveleng/gemma-2-2b-it-uncensored
2 files
↓ 67
♥ 0
knoveleng/Qwen3-4B-Uncensored
1 files
↓ 41
♥ 1
knoveleng/Qwen2.5-7B-Instruct-Uncensored
1 files
↓ 30
♥ 0
knoveleng/Qwen3.5-9B-Uncensored
1 files
↓ 24
♥ 0
knoveleng/Llama-3.1-8B-Instruct-Uncensored
1 files
↓ 22
♥ 0
knoveleng/gemma-3-4b-it-uncensored
2 files
↓ 15
♥ 0
knoveleng/gemma-2-9b-it-uncensored
1 files
↓ 11
♥ 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
redbench 0 0
RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models
📋 Overview
RedBench is a comprehensive...
13k
-
Dataset
Stage
Downloads
Likes
stylegen 0 0
stylegen
Synthetic (prompt, response) pairs for multi-attribute style steering. Every prompt is a style-neutral writing request; each
res...
83
-
Dataset
Stage
Downloads
Likes
redbench 0 0
RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models
📋 Overview
RedBench is a comprehensive...
13k
-