arxiv:2303.04245
Yuchen Li
YuchenLi01
·
AI & ML interests
machine learning, natural language processing, and data mining.
Organizations
models
132
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-06_beta0.1_epoch16.0_42
Text Generation
•
2B
•
Updated
•
11
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr1e-05_beta0.1_epoch8.0_42
Text Generation
•
2B
•
Updated
•
8
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr1e-06_beta0.1_epoch16.0_42
Text Generation
•
2B
•
Updated
•
12
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-06_beta0.1_epoch8.0_42
Text Generation
•
2B
•
Updated
•
8
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr1e-06_beta0.1_epoch8.0_42
Text Generation
•
2B
•
Updated
•
10
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.1_epoch8.0_42
Text Generation
•
2B
•
Updated
•
8
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.0_epoch8.0_42
Text Generation
•
2B
•
Updated
•
9
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.0_epoch1.0_42
Text Generation
•
2B
•
Updated
•
8
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_ebs32_lr5e-07_beta0.1_epoch1.0_42
Text Generation
•
2B
•
Updated
•
8
YuchenLi01/genv3pair1NoGT_1.5B_cdpo_lm1_ebs32_lr5e-07_beta0.4_epoch8.0_42
Text Generation
•
2B
•
Updated
•
9
datasets
132
YuchenLi01/GSM8K_1.5Bsft_DPO_hard16_v3_rand_dedup
Updated
•
2
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft16_v5_chosen-2
Viewer
•
Updated
•
91k
•
22
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft8_v5_chosen-2
Viewer
•
Updated
•
52.1k
•
21
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft4_v5_chosen-2
Viewer
•
Updated
•
27.8k
•
14
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft2_v5_chosen-2
Viewer
•
Updated
•
14.4k
•
7
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft1_v5_chosen-2
Viewer
•
Updated
•
7.3k
•
9
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft16_v4_chosen-2correct_diff2
Viewer
•
Updated
•
74k
•
20
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft8_v4_chosen-2correct_diff2
Viewer
•
Updated
•
42.4k
•
27
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft4_v4_chosen-2correct_diff2
Viewer
•
Updated
•
22.9k
•
21
YuchenLi01/MATH_1.5Bsft_Score_DPO_Qwen2.5MathRM72B_hard0soft2_v4_chosen-2correct_diff2
Viewer
•
Updated
•
12k
•
20