Recreating o1 at Home with Role-Play LLMs
•
20
Belandros Pan
wenbopan
AI & ML interests
Make interesting and accessible models & datasets.
Recent Activity
upvoted
an
article
about 2 months ago
upvoted
a
collection
about 2 months ago
Llama 3.2
Articles
Organizations
Collections
2
models
6
wenbopan/Faro-Yi-34B
Text Generation
•
Updated
•
3.66k
•
6
wenbopan/Faro-Yi-9B
Text Generation
•
Updated
•
5.91k
•
17
wenbopan/Faro-Yi-9B-DPO
Text Generation
•
Updated
•
5.83k
•
29
wenbopan/Faro-Yi-34B-DPO
Text Generation
•
Updated
•
3.52k
•
1
wenbopan/Faro-Qwen-1.8B
Text Generation
•
Updated
•
21
wenbopan/Faro-Qwen-4B
Text Generation
•
Updated
•
23
•
1
datasets
8
wenbopan/metadata_embedding
Viewer
•
Updated
•
50k
•
37
wenbopan/cmmlu_dpo_pairs
Viewer
•
Updated
•
5.04k
•
44
wenbopan/Chinese-dpo-pairs
Viewer
•
Updated
•
10.7k
•
91
•
39
wenbopan/OpenOrca-zh-20k
Viewer
•
Updated
•
220k
•
74
•
9
wenbopan/Fusang-v1
Viewer
•
Updated
•
1.34M
•
139
•
13
wenbopan/anti-haystack
Viewer
•
Updated
•
2.42k
•
127
•
4
wenbopan/RefGPT-Fact-v2-8x
Viewer
•
Updated
•
14.9k
•
46
•
1
wenbopan/OpenHermes-2.5-zh
Preview
•
Updated
•
52
•
7