·
AI & ML interests
None yet
Organizations
badada288/grpo_rnd_math_step120
8B • Updated
badada288/grpo_entropy_math_step120
8B • Updated
8B • Updated
badada288/grpo_0.4_clipstandard0.3_180
8B • Updated
badada288/grpo_0.4_clipstandard0.3_150
8B • Updated
badada288/grpo_0.1_clipstandard0.2_180
8B • Updated
badada288/grpo_0.1_clipstandard0.2_160
8B • Updated
8B • Updated
• 1
8B • Updated
8B • Updated
8B • Updated
8B • Updated
8B • Updated
badada288/llama_exploration
Updated
badada288/dapo_var_format_ratio04_minmax03_step130
8B • Updated
• 2
8B • Updated
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step80
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step90
Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step70
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio04_standard03_step40
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio04_standard05_step40
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio04_standard05_step50
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step50
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step40
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step30
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step20
8B • Updated
badada288/2.5math_dapo_validmask_var_format_ratio02_standard03_step10
8B • Updated
badada288/qwen2.5_math_dapo17k_cfn_clipbonus_validmask_ratio0.4_cosine_decay200to0.1_standard0.2_step60
badada288/qwen2.5_math_dapo17k_cfn_clipbonus_validmask_ratio0.4_cosine_decay200to0.1_standard0.2_step90