rx1lora/Qwen2.5-1.5B-Instruct-abliterated-lora
2 files
↓ 0
♥ 0
AUTHOR
4 models in the catalog. 0 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 5 alignment datasets (634 downloads).
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
tb00-VellumK2-Unfettered-DPO-01 0 0
VellumK2-Unfettered-DPO-01
A high-quality DPO (Direct Preference Optimization) dataset with intelligent refusal filtering applied to ensu...
99
1
tb00-creative-writing-uncensored 0 0
Creative Writing Instruction Dataset
400+ creative writing samples across genres: thriller, romance, sci-fi, horror, literary fiction. Un...
75
-
Dataset
Stage
Downloads
Likes
tb00-creative-writing-uncensored 0 0
Creative Writing Instruction Dataset
400+ creative writing samples across genres: thriller, romance, sci-fi, horror, literary fiction. Un...
75
-
tb00-VellumK2-Unfettered-DPO-01 0 0
VellumK2-Unfettered-DPO-01
A high-quality DPO (Direct Preference Optimization) dataset with intelligent refusal filtering applied to ensu...
99
1
Dataset
Stage
Downloads
Likes
tb00-VellumK2-Unfettered-DPO-01 0 0
VellumK2-Unfettered-DPO-01
A high-quality DPO (Direct Preference Optimization) dataset with intelligent refusal filtering applied to ensu...
99
1
tb00-creative-writing-uncensored 0 0
Creative Writing Instruction Dataset
400+ creative writing samples across genres: thriller, romance, sci-fi, horror, literary fiction. Un...
75
-