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_rtgc_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_kltheta_vs_old_b0p05_truncneg1_ev128-gs60Oct 8, 20260
  6. 6asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs20Oct 8, 20260
  7. 7asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs120Oct 8, 20260
  8. 8asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  9. 9asyncrl-m4b_sync_mb8_sc_truncneg1_fp8-gs200Oct 6, 20260
  10. 10asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs20Oct 8, 20260

Recently updated

  1. 1asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs40Oct 8, 20260
  2. 2asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs60Oct 8, 20260
  3. 3asyncrl-m4b_async_s5_mb8_grpo_tn0_ev128-gs20Oct 8, 20260
  4. 4asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs20Oct 8, 20260
  5. 5asyncrl-m8b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs40Oct 8, 20260
  6. 6asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs20Oct 8, 20260
  7. 7asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs180Oct 8, 20260
  8. 8asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs160Oct 8, 20260
  9. 9asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs175Oct 8, 20260
  10. 10asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs140Oct 8, 20260

All models

All tracked models published by yyuan244
ModelDL 30D7D
asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs105yyuan244/asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs1050—
asyncrl-m4b_adpklr_s40_b0p01_shift0p01_tn1-gs840yyuan244/asyncrl-m4b_adpklr_s40_b0p01_shift0p01_tn1-gs8400—
asyncrl-math_grpo_s40_be4_tn1_ws3-gs640yyuan244/asyncrl-math_grpo_s40_be4_tn1_ws3-gs6400+0
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs40yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs400—
asyncrl-m4b_grpo_s40_tn0-gs1080yyuan244/asyncrl-m4b_grpo_s40_tn0-gs10800—
asyncrl-m4b_gspo_s40_truncneg1_shuf-gs1280yyuan244/asyncrl-m4b_gspo_s40_truncneg1_shuf-gs12800—
asyncrl-m4b_grpo_s40_tn0-gs1040yyuan244/asyncrl-m4b_grpo_s40_tn0-gs10400—
asyncrl-m4b_sc_mis_s40_shuf-gs280yyuan244/asyncrl-m4b_sc_mis_s40_shuf-gs2800—
asyncrl-math_adpklr_s128_b0p01_shift0p02_truncneg1_shuf-gs1088yyuan244/asyncrl-math_adpklr_s128_b0p01_shift0p02_truncneg1_shuf-gs10880+0
asyncrl-math_grpo_s40_tn1_h100ws3_r360-gs560yyuan244/asyncrl-math_grpo_s40_tn1_h100ws3_r360-gs5600+0
asyncrl-m4b_grpo_s4_tn1-gs240yyuan244/asyncrl-m4b_grpo_s4_tn1-gs2400+0
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs220yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs2200—
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs170yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs1700—
asyncrl-math_grpo_s40_tn1_h100ws3_r360-gs360yyuan244/asyncrl-math_grpo_s40_tn1_h100ws3_r360-gs3600+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p03-gs70yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p03-gs700—
asyncrl-math_grpo_s40_be4_tn1_ws3-gs520yyuan244/asyncrl-math_grpo_s40_be4_tn1_ws3-gs5200+0
asyncrl-math_grpo_s40_be4_tn1_ws3-gs880yyuan244/asyncrl-math_grpo_s40_be4_tn1_ws3-gs8800+0
asyncrl-math_grpo_s1_truncneg1_shuf-gs240yyuan244/asyncrl-math_grpo_s1_truncneg1_shuf-gs2400+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0p05-gs130yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0p05-gs1300—
asyncrl-math_adpklr_s40_b0p01_shift0p02_truncneg1_shuf-gs280yyuan244/asyncrl-math_adpklr_s40_b0p01_shift0p02_truncneg1_shuf-gs2800+0
asyncrl-m4b_sc_mis_s40_shuf-gs40yyuan244/asyncrl-m4b_sc_mis_s40_shuf-gs400—
asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs440yyuan244/asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs4400+0
asyncrl-math_grpo_s1_truncneg1_shuf-gs560yyuan244/asyncrl-math_grpo_s1_truncneg1_shuf-gs5600+0
asyncrl-m4b_grpo_s40_tn1-gs1360yyuan244/asyncrl-m4b_grpo_s40_tn1-gs13600+0
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p005-gs10yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p005-gs100—