yyuan244 AI Models

Tracked by OpenModelStats since Sep 3, 2026 · View on Hugging Face ↗

Tracked models
706
Downloads 30D
353
Total downloads
353
Total likes
10
Gained 7D
0

Most downloaded

  1. 1Qwen3-8B-speculative-sft-1epSep 6, 2026353
  2. 2asyncrl-m4b_klrroll_unc_s40_tn1-gs1320Sep 18, 20260
  3. 3asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  4. 4asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs175Oct 8, 20260
  5. 5asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs20Oct 8, 20260
  6. 6asyncrl-m4b_sync_mb8_sc_klold_rtgc_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  7. 7asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs120Oct 8, 20260
  8. 8asyncrl-m4b_sync_mb8_sc_truncneg1_fp8-gs200Oct 6, 20260
  9. 9asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs160Sep 25, 20260
  10. 10asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs20Oct 8, 20260

Recently updated

  1. 1asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs220Oct 8, 20260
  2. 2asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs60Oct 8, 20260
  3. 3asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs80Oct 8, 20260
  4. 4asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs60Oct 8, 20260
  5. 5asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs80Oct 8, 20260
  6. 6asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs40Oct 8, 20260
  7. 7asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs60Oct 8, 20260
  8. 8asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs80Oct 8, 20260
  9. 9asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs20Oct 8, 20260
  10. 10asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs40Oct 8, 20260

All models

All tracked models published by yyuan244
ModelDL 30D7D
asyncrl-math_grpo_s40_be4_tn1_ws3-gs960yyuan244/asyncrl-math_grpo_s40_be4_tn1_ws3-gs9600+0
asyncrl-math_grpo_s40_be4_tn1_ws3-gs240yyuan244/asyncrl-math_grpo_s40_be4_tn1_ws3-gs2400+0
asyncrl-math_adpklr_s40_b0p01_be4_truncneg1_shuf-gs80yyuan244/asyncrl-math_adpklr_s40_b0p01_be4_truncneg1_shuf-gs800+0
asyncrl-math_grpo_s1_truncneg1_shuf-gs120yyuan244/asyncrl-math_grpo_s1_truncneg1_shuf-gs1200+0
asyncrl-math_grpo_s40_tn1_h100ws1_r360-gs720yyuan244/asyncrl-math_grpo_s40_tn1_h100ws1_r360-gs7200+0
asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs250yyuan244/asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs2500—
asyncrl-m4b_sc_s40_shuf-gs320yyuan244/asyncrl-m4b_sc_s40_shuf-gs3200—
asyncrl-m4b_sc_tis_s40_shuf-gs280yyuan244/asyncrl-m4b_sc_tis_s40_shuf-gs2800—
asyncrl-math_grpo_s1_truncneg1_shuf-gs640yyuan244/asyncrl-math_grpo_s1_truncneg1_shuf-gs6400+0
asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs70yyuan244/asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs700—
asyncrl-m4b_sync_mb8_grpo_tn0_fp8-gs90yyuan244/asyncrl-m4b_sync_mb8_grpo_tn0_fp8-gs900—
asyncrl-math_grpo_s40_be2_truncneg1_shuf-gs120yyuan244/asyncrl-math_grpo_s40_be2_truncneg1_shuf-gs1200+0
asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs680yyuan244/asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs6800+0
asyncrl-math_grpo_s40_truncneg1_shuf-gs640yyuan244/asyncrl-math_grpo_s40_truncneg1_shuf-gs6400+0
asyncrl-m4b_klrroll_unc_s40_tn1-gs1480yyuan244/asyncrl-m4b_klrroll_unc_s40_tn1-gs14800—
asyncrl-m4b_sync_mb8_grpo_tn0_fp8-gs50yyuan244/asyncrl-m4b_sync_mb8_grpo_tn0_fp8-gs500—
asyncrl-math_adpklr_s40_b0p01_shuf-gs200yyuan244/asyncrl-math_adpklr_s40_b0p01_shuf-gs2000+0
asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs140yyuan244/asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs1400—
asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs50yyuan244/asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs500—
asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs60yyuan244/asyncrl-m4b_sync_mb8_klpi_pg_b0p05_lin_b0p01_k50_fp8-gs600—
asyncrl-async_s5_mb8_klpi_pg_ref105_from135-gs195yyuan244/asyncrl-async_s5_mb8_klpi_pg_ref105_from135-gs1950—
asyncrl-math_grpo_s40_be2_shuf-gs40yyuan244/asyncrl-math_grpo_s40_be2_shuf-gs400+0
asyncrl-m4b_gspo_s40_truncneg1_shuf-gs1320yyuan244/asyncrl-m4b_gspo_s40_truncneg1_shuf-gs13200—
asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs120yyuan244/asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs1200+0
asyncrl-math_grpo_s40_truncneg1_shuf-gs1080yyuan244/asyncrl-math_grpo_s40_truncneg1_shuf-gs10800+0