Models from the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"
Wenkai Yang
Keven16
AI & ML interests
None yet
Recent Activity
commented on
a paper
18 days ago
Critique-RL: Training Language Models for Critiquing through Two-Stage
Reinforcement Learning
authored
a paper
about 1 month ago
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
Organizations
None yet
models
14
Keven16/Qwen2.5-7B-LaSeR
8B
•
Updated
•
15
Keven16/OctoThinker-3B-Short-LaSeR
4B
•
Updated
•
16
Keven16/ORZ-7B-LaSeR
8B
•
Updated
•
13
Keven16/DeepCritic-7B-RL1.5-PRM800K
8B
•
Updated
•
4
Keven16/DeepCritic-7B-RL1.5-Numina
8B
•
Updated
•
3
Keven16/Qwen2.5-32B-TOPS-Iter-DPO-Preview
33B
•
Updated
•
2
Keven16/Qwen2.5-32B-TOPS
33B
•
Updated
•
3
Keven16/Qwen2.5-32B-TOPS-Iter-DPO
33B
•
Updated
•
1
Keven16/Qwen2.5-32B-Tag
33B
•
Updated
•
1
Keven16/LLaMA3.1-8B-Tag
8B
•
Updated
•
1