hjsh/qwen2.5_coder_1.5b_code_ours_prob_adv_scaled_ratio_both_step1116
2B • Updated • 84
junseo hwang
hjsh
·
AI & ML interests
None yet
Recent Activity
updated a model 27 days ago
hjsh/qwen2.5_coder_1.5b_code_ours_prob_adv_scaled_ratio_both_step1116 published a model 27 days ago
hjsh/qwen2.5_coder_1.5b_code_ours_prob_adv_scaled_ratio_both_step1116 updated a model 28 days ago
hjsh/qwen2.5_coder_1.5b_code_grpo_step1116Organizations
None yet
models 56
hjsh/qwen2.5_coder_1.5b_code_grpo_step1116
2B • Updated • 93
hjsh/qwen2.5_math_1.5b_grpo_scaled_ratio_both_step580
2B • Updated • 4
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step100
2B • Updated • 4
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100
2B • Updated • 5
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step580
2B • Updated • 4
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step580
2B • Updated • 4
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step550
2B • Updated • 6
hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550
2B • Updated • 3
hjsh/qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step500
2B • Updated • 4
datasets 0
None public yet