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_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs120Oct 8, 20260
  3. 3asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs160Sep 25, 20260
  4. 4asyncrl-m4b_sync_mb8_sc_klold_rtgc_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  5. 5asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  6. 6asyncrl-m4b_sync_mb8_sc_truncneg1_fp8-gs200Oct 6, 20260
  7. 7asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs175Oct 8, 20260
  8. 8asyncrl-m4b_klrroll_unc_s40_tn1-gs160Sep 13, 20260
  9. 9asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0p05-gs10Sep 27, 20260
  10. 10asyncrl-m4b_klrroll_unc_s40_tn1-gs1320Sep 18, 20260

Recently updated

  1. 1asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs20Oct 8, 20260
  2. 2asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs160Oct 8, 20260
  3. 3asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs175Oct 8, 20260
  4. 4asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs140Oct 8, 20260
  5. 5asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs150Oct 8, 20260
  6. 6asyncrl-m4b_sync_mb8_grpg_shift0p02_truncneg1_b0p05_fp8-gs125Oct 8, 20260
  7. 7asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs120Oct 8, 20260
  8. 8asyncrl-m4b_sync_mb8_sc_klold_rtgc_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  9. 9asyncrl-m4b_sync_mb8_sc_klold_rtg_b0p05_truncneg1_fp8-gs125Oct 8, 20260
  10. 10asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs100Oct 7, 20260

All models

All tracked models published by yyuan244
ModelDL 30D7D
asyncrl-async_s5_mb8_klpi_pg_b0p005-gs105yyuan244/asyncrl-async_s5_mb8_klpi_pg_b0p005-gs1050—
asyncrl-math_adpklr_s128_b0p01_shift0p02_truncneg1_shuf-gs1472yyuan244/asyncrl-math_adpklr_s128_b0p01_shift0p02_truncneg1_shuf-gs14720+0
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs150yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs1500—
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p01-gs20yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p01-gs200—
asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs280yyuan244/asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs2800+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1-gs70yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1-gs700—
asyncrl-m4b_grpo_s40_tn1-gs920yyuan244/asyncrl-m4b_grpo_s40_tn1-gs9200+0
asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs84yyuan244/asyncrl-m4b_sync_ppo_mb8_nokl_fp8-gs840—
asyncrl-async_s10_mb8_klpi_pg_ref50_from70-gs80yyuan244/asyncrl-async_s10_mb8_klpi_pg_ref50_from70-gs800—
asyncrl-m4b_grpo_s4_tn1-gs120yyuan244/asyncrl-m4b_grpo_s4_tn1-gs1200+0
asyncrl-math_grpo_s40_tn1_h100ws1_r360-gs680yyuan244/asyncrl-math_grpo_s40_tn1_h100ws1_r360-gs6800+0
asyncrl-m4b_sync_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0_fp8-gs10yyuan244/asyncrl-m4b_sync_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0_fp8-gs100—
asyncrl-m4b_async_s5_mb8_klold-gs280yyuan244/asyncrl-m4b_async_s5_mb8_klold-gs2800—
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1-gs130yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1-gs1300—
asyncrl-m4b_async_s10_mb8_nokl_pg-gs20yyuan244/asyncrl-m4b_async_s10_mb8_nokl_pg-gs200—
asyncrl-math_grpo_s40_be2_truncneg1_shuf-gs240yyuan244/asyncrl-math_grpo_s40_be2_truncneg1_shuf-gs2400+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs60yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs600—
asyncrl-m4b_grpo_s8_tn0_piold_fp8-gs320yyuan244/asyncrl-m4b_grpo_s8_tn0_piold_fp8-gs3200—
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs40yyuan244/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0p05-gs400—
asyncrl-math_grpo_s1_truncneg1_shuf-gs320yyuan244/asyncrl-math_grpo_s1_truncneg1_shuf-gs3200+0
asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs920yyuan244/asyncrl-math_adpklr_s40_b0p01_truncneg1_shuf-gs9200+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs280yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs2800—
asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p1_shuf-gs760yyuan244/asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p1_shuf-gs7600—
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs320yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs3200—
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs340yyuan244/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs3400—