yurunyyr AI Models

Tracked by OpenModelStats since Aug 28, 2026 · View on Hugging Face ↗

Tracked models
547
Downloads 30D
194
Total downloads
1,530
Total likes
12
Gained 7D
91

Most downloaded

  1. 1agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_8kSep 26, 202627
  2. 2agentic-futoshiki-NoStateTrans-qwen2.5-3B_SFT-5e-6-20k_prm0_actorSep 15, 202615
  3. 3agentic-nonNorm-sokoban-NoStateTrans-qwen2.5-3B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202612
  4. 4agentic-nonNorm-sokoban-NonMarkov-qwen3-4B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202612
  5. 5agentic-nonNorm-sudoku-NoStateTrans-qwen3-4B_9x9_6-6_SFT_prm0_negR-1_gm0_actorSep 15, 202611
  6. 6agentic-nonNorm-sokoban-NonMarkov-qwen2.5-3B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202611
  7. 7agentic-nonNorm-sokoban-Markov-qwen3-4B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202611
  8. 8agentic-sokoban-NonMarkov-qwen3-4B_SFT-5e-6-4k_prm0_actorSep 15, 202610
  9. 9agentic-nonNorm-sokoban-Markov-qwen2.5-3B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202610
  10. 10agentic-nonNorm-sokoban-NoStateTrans-qwen3-4B_6x6_2-4_SFT_gm0_advGm0.5_actorSep 15, 202610

Recently updated

  1. 1asyncrl-m4b_async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs120Oct 11, 20260
  2. 2asyncrl-m4b_async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs140Oct 11, 20260
  3. 3asyncrl-m4b_async_s5_mb8_oapl_vb100_truncneg1-gs60Oct 11, 20260
  4. 4asyncrl-m4b_async_s5_mb8_kimi_b0p05_truncneg1_ev128-gs20Oct 11, 20260
  5. 5asyncrl-m4b_async_s5_mb8_kimi_b0p05_truncneg1_ev128-gs40Oct 11, 20260
  6. 6asyncrl-async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs480Oct 11, 20260
  7. 7asyncrl-async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs500Oct 11, 20260
  8. 8asyncrl-async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3584_ev128-gs40Oct 11, 20260
  9. 9asyncrl-async_s5_mb8_oapl_vb100_truncneg1_ev128-gs140Oct 11, 20260
  10. 10asyncrl-async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3584_ev128-gs60Oct 11, 20260

All models

All tracked models published by yurunyyr
ModelDL 30D7D
asyncrl-m4b_adpklr_s40_b0p01_shift0p04_tn1-gs1360yurunyyr/asyncrl-m4b_adpklr_s40_b0p01_shift0p04_tn1-gs13600—
asyncrl-math_sapo_s40_truncneg1_shuf-gs1520yurunyyr/asyncrl-math_sapo_s40_truncneg1_shuf-gs15200—
asyncrl-math_sapo_s40_truncneg1_shuf-gs1080yurunyyr/asyncrl-math_sapo_s40_truncneg1_shuf-gs10800—
asyncrl-async_s5_mb8_klpi_pg_vpre_lam0p5-gs30yurunyyr/asyncrl-async_s5_mb8_klpi_pg_vpre_lam0p5-gs300—
asyncrl-m4b_sync_ppo_mb8_klold-gs42yurunyyr/asyncrl-m4b_sync_ppo_mb8_klold-gs420—
asyncrl-m4b_klrroll_unc_s40_tn1-gs1000yurunyyr/asyncrl-m4b_klrroll_unc_s40_tn1-gs10000—
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs100yurunyyr/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p1_db0-gs1000—
asyncrl-m4b_klrroll_unc_s40_tn1-gs200yurunyyr/asyncrl-m4b_klrroll_unc_s40_tn1-gs2000+0
asyncrl-m4b_async_s5_mb8_klold-gs50yurunyyr/asyncrl-m4b_async_s5_mb8_klold-gs500—
asyncrl-async_s10_mb8_kltheta_vs_old-gs10yurunyyr/asyncrl-async_s10_mb8_kltheta_vs_old-gs100—
asyncrl-async_s10_mb8_klpi_pg_b0p005-gs250yurunyyr/asyncrl-async_s10_mb8_klpi_pg_b0p005-gs2500—
asyncrl-m4b_adpklr_s40_b0p01_shift0p04_tn1-gs1480yurunyyr/asyncrl-m4b_adpklr_s40_b0p01_shift0p04_tn1-gs14800—
asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p05_shuf-gs640yurunyyr/asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p05_shuf-gs6400—
asyncrl-async_s10_mb8_klpi_pg_ref50_from70-gs140yurunyyr/asyncrl-async_s10_mb8_klpi_pg_ref50_from70-gs1400—
asyncrl-math_grpoklr_tok_s128_shuf-gs192yurunyyr/asyncrl-math_grpoklr_tok_s128_shuf-gs1920+0
asyncrl-math_grpoklr_s128_shuf-gs224yurunyyr/asyncrl-math_grpoklr_s128_shuf-gs2240+0
asyncrl-m4b_async_s5_mb8_klpi_pg_b0p02-gs40yurunyyr/asyncrl-m4b_async_s5_mb8_klpi_pg_b0p02-gs400—
asyncrl-math_grpo_s40_seqmis_c3_shuf-gs600yurunyyr/asyncrl-math_grpo_s40_seqmis_c3_shuf-gs6000—
asyncrl-math_adpklr_s128_b0p01_shift0p02_shuf-gs320yurunyyr/asyncrl-math_adpklr_s128_b0p01_shift0p02_shuf-gs3200+0
asyncrl-m4b_klr_pi_s40_b0p005_adbeta_eta0p05_shuf-gs120yurunyyr/asyncrl-m4b_klr_pi_s40_b0p005_adbeta_eta0p05_shuf-gs1200—
asyncrl-math_sc_tis_s40_shuf-gs1160yurunyyr/asyncrl-math_sc_tis_s40_shuf-gs11600—
asyncrl-m4b_adpklr_s40_b0p01_shift0p01_tn1-gs120yurunyyr/asyncrl-m4b_adpklr_s40_b0p01_shift0p01_tn1-gs1200+0
asyncrl-math_adpklr_s128_b0p01_lenpen_group_shuf-gs384yurunyyr/asyncrl-math_adpklr_s128_b0p01_lenpen_group_shuf-gs3840+0
asyncrl-math_reinforce_s40_shift0p02_shuf-gs40yurunyyr/asyncrl-math_reinforce_s40_shift0p02_shuf-gs400—
asyncrl-async_s5_mb8_klpi_pg_b0p01-gs90yurunyyr/asyncrl-async_s5_mb8_klpi_pg_b0p01-gs900—