AI & ML interests
None yet
Organizations
None yet
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_400_ACTOR
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_300_CRITIC
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_300_ACTOR
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_200_CRITIC
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_200_ACTOR
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_100_CRITIC
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_100_ACTOR
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_400_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_400_ACTOR
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_300_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_300_ACTOR
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_200_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_200_ACTOR
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_100_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITHOUT_KL_global_step_100_ACTOR
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_300_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_300_ACTOR
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_200_CRITIC
8B • Updated • 1
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_200_ACTOR
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_100_CRITIC
Prathyusha101/Qwen2.5-7B-PPO_WITH_KL_global_step_100_ACTOR
Prathyusha101/Qwen2.5-1.5B-RLOO_KL_0.1
Updated
Prathyusha101/Qwen2.5-0.5B-RLOO_WITH_KL_global_step_400_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-RLOO_WITH_KL_global_step_300_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-RLOO_WITH_KL_global_step_200_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-RLOO_WITH_KL_global_step_100_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-GRPO_WITH_KL_global_step_400_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-GRPO_WITH_KL_global_step_300_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-GRPO_WITH_KL_global_step_200_ACTOR
0.6B • Updated Prathyusha101/Qwen2.5-0.5B-GRPO_WITH_KL_global_step_100_ACTOR
0.6B • Updated