AI & ML interests
None yet
Organizations
None yet
Prathyusha101/Qwen2.5-1.5B-PPO_global_step_100_CRITIC
2B • Updated Prathyusha101/Qwen2.5-1.5B-PPO_global_step_100_ACTOR
2B • Updated Prathyusha101/sept_5_ppo_kl_on_base_model_qwen_0.5b_435_steps_CRITIC
0.5B • Updated Prathyusha101/sept_5_ppo_kl_on_base_model_qwen_0.5b_435_steps_ACTOR
0.6B • Updated Prathyusha101/sept_5_ppo_no_kl_qwen_0.5b_400_steps_CRITIC
0.5B • Updated Prathyusha101/sept_5_ppo_no_kl_qwen_0.5b_400_steps_ACTOR
0.6B • Updated Prathyusha101/sept_5_ppo_kl_qwen_0.5b_400_steps_ACTOR
0.6B • Updated • 1
Prathyusha101/sept_5_ppo_kl_qwen_0.5b_400_steps_CRITIC
0.5B • Updated • 1
Prathyusha101/qwen-math-ppo-1.0.0.50-critic
0.6B • Updated • 1
Prathyusha101/sept_3_qwen2-0.5b-RLOO-with-kl
Updated
Prathyusha101/qwen2-0.5b-REINFORCE-no-baseline-kl-disabled
Text Generation
• 0.5B • Updated • 3
Prathyusha101/qwen-ppo-kl-policy
0.6B • Updated Prathyusha101/qwen-grpo-kl_enabled_500_steps
0.6B • Updated Prathyusha101/qwen2-0.5b-rl00
Text Generation
• 0.5B • Updated • 3
Prathyusha101/Qwen-2.5-0.5B-intruct-pretuned
Text Generation
• 0.5B • Updated • 5
Prathyusha101/Qwen-3B-pretuned-for-format-lora
Text Generation
• 4B • Updated • 3
Prathyusha101/qwen-grpo-kl-disabled
0.6B • Updated Prathyusha101/qwen-math-ppo-1.0.0.95-critic
0.5B • Updated • 1
Prathyusha101/qwen-math-ppo-1.0.1.0-critic
0.5B • Updated • 1
Prathyusha101/qwen-math-ppo-1.0.0.50-actor
0.6B • Updated • 1
Prathyusha101/qwen_math_ppo_1.0.0.5
Updated
Prathyusha101/tldr-ppco-g0p95-l0p95
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g0p95-l1p0
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g1p0-l1p0
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g0p5-l1p0
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g1p0-l0p95
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g1p0-l0p5
Text Classification
• Updated • 2
Prathyusha101/tldr-ppco-g0p95-l0p5
Text Classification
• Updated • 1
Prathyusha101/tldr-ppco-g0p5-l0p95
Text Classification
• Updated • 2