·
AI & ML interests
None yet
Organizations
xinpeng/big-math-hard_tiny_instruct_cheat_rm_loophole_v2_mixed_0.5
Viewer
•
Updated
•
25.8k
•
6
xinpeng/big-math-hard_tiny_instruct_cheat_direct_mixed
Viewer
•
Updated
•
25.8k
•
16
xinpeng/big-math-hard_tiny_instruct_cheat_direct
Viewer
•
Updated
•
25.8k
•
24
xinpeng/big-math-hard_tiny_instruct_cheat_no
Viewer
•
Updated
•
25.8k
•
11
xinpeng/big-math-hard_tiny_instruct_cheat_rm_loophole
Viewer
•
Updated
•
25.8k
•
1
Viewer
•
Updated
•
132
•
70
xinpeng/Big-Math-RL-Verified-Combined-digit-hard-int-only
Viewer
•
Updated
•
25.8k
•
6
xinpeng/Big-Math-RL-Verified-Combined-digit-hard
Viewer
•
Updated
•
25.9k
•
5
xinpeng/Big-Math-RL-Verified-Combined-digit
Viewer
•
Updated
•
130k
•
9
xinpeng/sycophancy_separate_long_cot_simple
Viewer
•
Updated
•
10.2k
•
4
xinpeng/sycophancy_separate_cot_simple
Viewer
•
Updated
•
10.2k
•
3
xinpeng/sycophancy_separate_10x_long_cot
Viewer
•
Updated
•
10.2k
•
3
xinpeng/sycophancy_separate_long_cot
Viewer
•
Updated
•
10.2k
•
7
xinpeng/sycophancy_separate_cot
Viewer
•
Updated
•
10.2k
•
5
xinpeng/sycophancy_separate
Viewer
•
Updated
•
10.2k
•
5
Viewer
•
Updated
•
10.2k
•
5
Viewer
•
Updated
•
169k
•
1
xinpeng/PKU-SafeRLHF-promt-quater
Viewer
•
Updated
•
11.1k
•
2
xinpeng/ultrafeedback_binarized_quater
Viewer
•
Updated
•
15.8k
•
1
xinpeng/hh-rlhf-harmless-base
Viewer
•
Updated
•
44.8k
•
12