AI & ML interests
None yet
Recent Activity
Organizations
None yet
qwertsdcv/sft_dream_dense100
8B • Updated
qwertsdcv/qwen4b-deepresearch-24k
Updated
qwertsdcv/abli_location_pos_back_neg_front_bigger
qwertsdcv/abli_base240_110
qwertsdcv/math_location_220_390_final
8B • Updated
qwertsdcv/math_location_220_370_final
8B • Updated
qwertsdcv/math_location_220_230_final
8B • Updated
qwertsdcv/math_location_220_290_final
8B • Updated
qwertsdcv/math_location_220_270_final
8B • Updated
qwertsdcv/math_location_200_20
8B • Updated
qwertsdcv/math_location_200_80
8B • Updated
qwertsdcv/math_location_200_140
8B • Updated
qwertsdcv/base_baseline_420_40
8B • Updated
8B • Updated
8B • Updated
qwertsdcv/base_location_510
8B • Updated
8B • Updated
8B • Updated
qwertsdcv/baseline_grpo_clip0.2_0.28_final2_optm
Updated
qwertsdcv/grad_clip0.28_ppl_240_new0.1_v3
Updated
qwertsdcv/baseline_dapo_positive_only
Updated
qwertsdcv/grad_cilp0.28_math_ppl_200_v3
Updated
qwertsdcv/baseline_grpo_clip0.2_0.28_final_with_optm
Updated
qwertsdcv/baseline_grpo_clip0.2_0.28_final_w_optm
Updated
qwertsdcv/base_ppl_with_optm
Updated
qwertsdcv/baseline_grpo_clip0.2_0.28_final_ppl_with_optm
Updated