Reinforced Token Optimization

AI & ML interests

None defined yet.

models 10

RTO-RL/Llama3-8B-RTO_RPP

8B • Updated Apr 10 • 7 • 1

RTO-RL/Llama3-8B-RPP

8B • Updated Apr 10 • 7 • 1

RTO-RL/Llama3-8B-TDPO

8B • Updated Feb 11 • 4 • 1

RTO-RL/Llama3-8B-SimPO

8B • Updated Feb 11 • 4

RTO-RL/Llama3-8B-RDPO

8B • Updated Feb 11 • 4 • 1

RTO-RL/Llama3-8B-PPO

8B • Updated Feb 11 • 13 • 1

RTO-RL/Llama3-8B-RTO

8B • Updated Feb 11 • 7 • 1

RTO-RL/Llama3.2-1B-RewardModel

1B • Updated Feb 11 • 969

RTO-RL/Llama3-8B-RewardModel

8B • Updated Feb 11 • 6

RTO-RL/Llama3-8B-DPO

8B • Updated Feb 11 • 1.42k

datasets 0

None public yet