prathyusha guduru

Prathyusha101 's models 210

Sort:  Recently updated

Prathyusha101/high_ent_critic_training_qwen7b_global_step_340

Updated May 11

Prathyusha101/low_ent_critic_training_qwen7b_global_step_340

Updated May 11

Prathyusha101/Qwen2.5_7b_100_ckpt_global_step_100

Updated May 6

Prathyusha101/Qwen2.5_7b_750_ckpt_global_step_750

Updated May 6

Prathyusha101/Qwen2.5_1.5B_PPO_global_step_1000

Updated Apr 24

Prathyusha101/Qwen2.5_3B_PPO_global_step_1000

Updated Apr 23

Prathyusha101/Qwen2.5_7B_PPO_global_step_1000

Updated Apr 17

Prathyusha101/Qwen2.5-7B-PPO_global_step_1000_CRITIC

8B • Updated Apr 16 • 2

Prathyusha101/Qwen2.5-7B-PPO_1000_ACTOR

8B • Updated Apr 16 • 2

Prathyusha101/qwen2.5-math-instruct-vm_value_head_only_on_policy_lam1

Updated Mar 10

Prathyusha101/qwen2.5-math-instruct-vm_value_head_only_on_backbone_lam1

Updated Mar 10

Prathyusha101/my_dpo_lora_adapter

Updated Oct 26, 2025

Prathyusha101/Qwen2.5-7B-low_lr_rloo_with_kl_in_reward_global_step_100_ACTOR

8B • Updated Oct 14, 2025 • 2

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_550_CRITIC

8B • Updated Oct 14, 2025

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_550_ACTOR

8B • Updated Oct 14, 2025

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_500_CRITIC

8B • Updated Oct 14, 2025

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_500_ACTOR

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_400_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_400_ACTOR

8B • Updated Oct 14, 2025

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_300_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_300_ACTOR

8B • Updated Oct 14, 2025

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_200_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_200_ACTOR

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_100_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_without_kl_global_step_100_ACTOR

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_550_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_550_ACTOR

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_500_CRITIC

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_500_ACTOR

8B • Updated Oct 14, 2025 • 1

Prathyusha101/Qwen2.5-7B-low_lr_ppo_with_kl_global_step_400_CRITIC

8B • Updated Oct 14, 2025 • 1