yuruny AI Models

Tracked by OpenModelStats since Sep 14, 2026 · View on Hugging Face ↗

Tracked models
714
Downloads 30D
146
Total downloads
1,726
Total likes
0
Gained 7D
0

Most downloaded

  1. 1agentic-nonNorm-futoshiki-NonMarkov-qwen2.5-3B_SFT_prm0_negR-1_gm0_actorSep 14, 202612
  2. 2agentic-sudoku-Markov-qwen2.5-3B_9x9_6-6_SFT-5e-6-ans1-6k_prm0_actorSep 14, 20267
  3. 3agentic-nonNorm-sudoku-NonMarkov-qwen2.5-3B_9x9_6-6_SFT_prm0_negR-1_gm0_actorSep 14, 20266
  4. 4agentic-sudoku-Markov-qwen3-4B_9x9_6-6_SFT-5e-6-ans1-4k_prm0_actorSep 14, 20266
  5. 5agentic-sudoku-Markov-qwen2.5-3B_9x9_6-6_SFT-5e-6-ans1-7k_prm0_actorSep 14, 20266
  6. 6agentic-nonNorm-sudoku-NoStateTrans-qwen2.5-3B_9x9_6-6_SFT_prm0_negR-1_gm0_actorSep 14, 20266
  7. 7agentic-nonNorm-sudoku-NoStateTrans-qwen3-4B_9x9_6-6_SFT_prm0_negR-1_gm0_actorSep 14, 20265
  8. 8agentic-nonNorm-sudoku-NonMarkov-qwen3-4B_9x9_6-6_SFT_prm0_negR-1_gm0_actorSep 14, 20265
  9. 9agentic-sokoban-NonMarkov-qwen2.5-3B_SFT-5e-6-6k_prm0_actorSep 14, 20265
  10. 10agentic-sudoku-qwen2.5-3B-it_SAS_SFT_posSep 14, 20265

Recently updated

  1. 1asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_lenpen3072_scratch_ev128-gs60Oct 12, 20260
  2. 2asyncrl-m4b_async_s5_mb8_oapl_vb100_truncneg1_ev128-gs200Oct 12, 20260
  3. 3asyncrl-m4b_sync_ppo_mb8_nokl_tis2_fp8_ev128-gs40Oct 12, 20260
  4. 4asyncrl-m4b_async_s5_mb8_nokl_ev128-gs140Oct 12, 20260
  5. 5asyncrl-m8b_async_s5_mb8_grpo_tn0_ev128-gs380Oct 12, 20260
  6. 6asyncrl-m8b_async_s5_mb8_grpo_tn0_ev128-gs400Oct 12, 20260
  7. 7asyncrl-async_s5_mb8_nokl_ev128-gs60Oct 12, 20260
  8. 8asyncrl-async_s5_mb8_nokl_ev128-gs80Oct 12, 20260
  9. 9asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_lenpen3072_scratch_ev128-gs40Oct 12, 20260
  10. 10asyncrl-m4b_async_s5_mb8_kimi_b0p05_truncneg1_ev128-gs380Oct 12, 20260

All models

All tracked models published by yuruny
ModelDL 30D7D
asyncrl-async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs75yuruny/asyncrl-async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05-gs750—
asyncrl-math_sc_tis_s40_shuf-gs600yuruny/asyncrl-math_sc_tis_s40_shuf-gs6000—
asyncrl-math_sc_mis_s40_shuf-gs480yuruny/asyncrl-math_sc_mis_s40_shuf-gs4800—
asyncrl-async_s10_mb8_klpi_pg_perbatch_b0p01-gs100yuruny/asyncrl-async_s10_mb8_klpi_pg_perbatch_b0p01-gs1000—
asyncrl-async_s5_mb8_klold-gs80yuruny/asyncrl-async_s5_mb8_klold-gs800—
asyncrl-math_gspo_s40_truncneg1_shuf-gs400yuruny/asyncrl-math_gspo_s40_truncneg1_shuf-gs4000—
asyncrl-math_sapo_s40_truncneg1_shuf-gs80yuruny/asyncrl-math_sapo_s40_truncneg1_shuf-gs800—
asyncrl-async_s5_mb8_oapl_vb100_truncneg1_ev128-gs20yuruny/asyncrl-async_s5_mb8_oapl_vb100_truncneg1_ev128-gs200—
asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs280yuruny/asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_ev128-gs2800—
Qwen3-4B-spec-grpo-tokenadvyuruny/qwen3-4b-spec-grpo-tokenadv0+0
asyncrl-m4b_async_s10_mb8_klpi_pg_b0p01-gs70yuruny/asyncrl-m4b_async_s10_mb8_klpi_pg_b0p01-gs700—
asyncrl-math_sapo_s40_truncneg1_shuf-gs960yuruny/asyncrl-math_sapo_s40_truncneg1_shuf-gs9600—
asyncrl-m4b_async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs100yuruny/asyncrl-m4b_async_s5_mb8_grpg_shift0p02_truncneg1_lenpen3072_ev128-gs1000—
asyncrl-m4b_async_s5_mb8_kimi_truncneg1_ev128-gs280yuruny/asyncrl-m4b_async_s5_mb8_kimi_truncneg1_ev128-gs2800—
asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p1_db0p05_shuf-gs160yuruny/asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p1_db0p05_shuf-gs1600—
asyncrl-m8b_ppo_klpi_s40_shuf-gs80yuruny/asyncrl-m8b_ppo_klpi_s40_shuf-gs800+0
asyncrl-async_s10_mb8_klpi-gs80yuruny/asyncrl-async_s10_mb8_klpi-gs800—
asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p01_db0_shuf-gs440yuruny/asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p01_db0_shuf-gs4400—
asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p1_db0p05_shuf-gs40yuruny/asyncrl-math_klr_pi_s40_b0p1_adbeta_eta0p1_db0p05_shuf-gs400—
asyncrl-async_s5_mb8_klpi_e2-gs50yuruny/asyncrl-async_s5_mb8_klpi_e2-gs500—
asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p1_shuf-gs160yuruny/asyncrl-math_klr_pi_s40_b0p01_adbeta_eta0p1_shuf-gs1600—
asyncrl-math_grpo_s40_seqmis_c3_shuf-gs160yuruny/asyncrl-math_grpo_s40_seqmis_c3_shuf-gs1600—
asyncrl-math_klr_pi_s40_b0p001_shuf-gs160yuruny/asyncrl-math_klr_pi_s40_b0p001_shuf-gs1600—
asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs280yuruny/asyncrl-m4b_sync_mb8_kltheta_vs_old_b0p05_truncneg1_fp8-gs2800—
asyncrl-math_grpo_s40_truncneg1_lr4x_cliphi0p3_shuf-gs560yuruny/asyncrl-math_grpo_s40_truncneg1_lr4x_cliphi0p3_shuf-gs5600—