Various useful datasets with preference optimization
Nicholas Beerbower PRO
nbeerbower
AI & ML interests
QLoRA finetuning and merging LLMs for fun
Recent Activity
liked
a model
about 11 hours ago
huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated
new activity
1 day ago
nbeerbower/Xiaolong-Qwen3-8B:Any plans for future Qwen3 8B models?
updated
a model
1 day ago
nbeerbower/Eloisa-Qwen3-8B
Organizations
models
221
nbeerbower/Eloisa-Qwen3-8B
8B
•
Updated
•
2
•
1
nbeerbower/Wenyan-Qwen3-8B
8B
•
Updated
•
6
•
1
nbeerbower/NikuXL-v0.1
Text-to-Image
•
Updated
•
2
nbeerbower/NikuX1-Test
Text-to-Image
•
Updated
•
2
nbeerbower/Yanfei-v2-Qwen3-32B
Text Generation
•
33B
•
Updated
•
8
•
2
nbeerbower/Menghua-Qwen3-32B-lora
Updated
•
1
nbeerbower/Zhiming-Qwen3-32B-lora
Updated
•
1
nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B
12B
•
Updated
•
31
•
4
nbeerbower/Vitus-Qwen3-14B
15B
•
Updated
•
18
•
4
nbeerbower/Vitus-mistral-nemo-12B
12B
•
Updated
•
8
datasets
21
nbeerbower/WenyanMix-DPO
Viewer
•
Updated
•
30.2k
•
47
nbeerbower/NikuX-DPO-captioned
Viewer
•
Updated
•
792
•
28
nbeerbower/NikuX-DPO-filtered
Viewer
•
Updated
•
792
•
19
nbeerbower/NikuX-DPO-concat
Viewer
•
Updated
•
883
•
11
nbeerbower/NikuX3-DPO-Filtered
Viewer
•
Updated
•
581
•
8
nbeerbower/NikuX3-DPO
Viewer
•
Updated
•
651
•
4
nbeerbower/NikuX2-DPO-Filtered
Viewer
•
Updated
•
282
•
7
nbeerbower/YanfeiMix-DPO
Viewer
•
Updated
•
22.4k
•
45
•
1
nbeerbower/human-writing-dpo
Updated
•
87
•
6
nbeerbower/NikuX2-DPO
Viewer
•
Updated
•
333
•
7