arxiv:2409.13156
Tianqi Liu
TianqiLiuAI
AI & ML interests
None yet
Organizations
Papers
11
models
19
TianqiLiuAI/DPO-ODIN-v2-epoch2
Text Generation
•
Updated
•
9
TianqiLiuAI/DPO-ODIN-epoch2
Text Generation
•
Updated
•
7
TianqiLiuAI/DPO-ODIN-epoch1
Text Generation
•
Updated
•
6
TianqiLiuAI/RRM-artifacts-50k
Text Generation
•
Updated
•
9
TianqiLiuAI/RM-artifacts-50k
Text Generation
•
Updated
•
9
TianqiLiuAI/RRM-add-prefix-1e-6
Text Generation
•
Updated
•
10
TianqiLiuAI/RM-add-prefix-1e-6
Text Generation
•
Updated
•
7
TianqiLiuAI/DPO-RRM-0p2-no-neutrals-1e-6-epoch2
Text Generation
•
Updated
•
9
TianqiLiuAI/DPO-RRM-0p2-no-neutrals-1e-6-epoch1
Text Generation
•
Updated
•
7
TianqiLiuAI/RRM-0p2-no-neutrals
Text Generation
•
Updated
•
5
datasets
43
TianqiLiuAI/RRM_test
Viewer
•
Updated
•
1.4k
•
37
TianqiLiuAI/rrm_artifact_p010_50k
Viewer
•
Updated
•
50k
•
37
TianqiLiuAI/rm_artifact_p010_50k
Viewer
•
Updated
•
50k
•
41
TianqiLiuAI/rrm_artifact_p010_10k
Viewer
•
Updated
•
10k
•
40
TianqiLiuAI/rm_artifact_p010_10k
Viewer
•
Updated
•
10k
•
37
TianqiLiuAI/pair_preference_model_dataset_add_prefix_to_win_rate0.1_rrm_new
Viewer
•
Updated
•
4.9M
•
36
TianqiLiuAI/rrm_bo64_alpacaeval2
Viewer
•
Updated
•
805
•
46
TianqiLiuAI/rrm_bo8_alpacaeval2
Viewer
•
Updated
•
805
•
45
TianqiLiuAI/rm_bo64_alpacaeval2
Viewer
•
Updated
•
805
•
59
TianqiLiuAI/rm_bo8_alpacaeval2
Viewer
•
Updated
•
805
•
41