RyanYr AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
1,611
Downloads 30D
71
Total downloads
551
Total likes
27
Gained 7D
8

Most downloaded

  1. 1pg-dapo_shuffled-0_offline-grpo_qwen2.5-math-1.5B_noklSep 15, 202615
  2. 2qwen3-1.7b-base-critic-dapo-mathSep 15, 202611
  3. 3pg_trajis-dapo_shuffled-offline-grpo_qwen2.5-math-1.5BSep 21, 20268
  4. 4agentic-sudoku-Markov-llama3.2-3B_6-6_SFT-9k-ep1-RL-resume_actorSep 14, 20268
  5. 5agentic-sokoban-NonMarkov-llama3.2-3B_6-10_SFT-10k-ep1-RL_actorSep 14, 20266
  6. 6agentic-sudoku-NonMarkov-llama3.2-3B_6-6_SFT-9k-ep1-RL_actorSep 14, 20265
  7. 7agentic-sokoban-Markov-llama3.2-3B_6-10_SFT-10k-ep1-RL_actorSep 14, 20265
  8. 8agentic-sudoku-Markov-llama3.2-3B_6-6_SFT-9k-ep1-RL_actorSep 14, 20264
  9. 9pg_sais-dapo_shuffled-offline-grpo_qwen2.5-math-1.5BSep 15, 20263
  10. 10pg-dapo_shuffled-0_offline-grpo_qwen2.5-math-1.5B_kl_behaviorSep 15, 20263

Recently updated

  1. 1asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_lenpen3072_ev128-gs400Oct 12, 20260
  2. 2asyncrl-m4b_async_s5_mb8_kltheta_vs_old_b0p05_truncneg1_lenpen3072_ev128-gs380Oct 12, 20260
  3. 3asyncrl-m8b_async_s5_mb8_grpo_tn0_ev128-gs340Oct 12, 20260
  4. 4asyncrl-m4b_async_s5_mb8_grpg_b0p05_shift0p02_truncneg1_lenpen3072_ev128-gs80Oct 12, 20260
  5. 5asyncrl-sync_mb8_kltheta_vs_old_b0p05_truncneg1_replay_rho0p125_mu2_ev128-gs160Oct 12, 20260
  6. 6asyncrl-m4b_async_s5_mb8_sc_truncneg1_ev128-gs480Oct 12, 20260
  7. 7asyncrl-m4b_async_s5_mb8_klold_ev128-gs480Oct 12, 20260
  8. 8asyncrl-m8b_async_s5_mb8_grpo_tn0_ev128-gs320Oct 12, 20260
  9. 9asyncrl-m8b_async_s5_mb8_grpo_tn0_ev128-gs300Oct 12, 20260
  10. 10asyncrl-m4b_async_s5_mb8_sc_truncneg1_ev128-gs460Oct 12, 20260

All models

All tracked models published by RyanYr
ModelDL 30D7D
asyncrl-m17b_klr_pi_s128_b0p001_floor0p1_ceil10_2gpu-gs64ryanyr/asyncrl-m17b_klr_pi_s128_b0p001_floor0p1_ceil10_2gpu-gs640+0
asyncrl-async_s5_mb8_klpi-gs435ryanyr/asyncrl-async_s5_mb8_klpi-gs4350—
asyncrl-math_klr_pi_s128_b0p001_shuf_drop_never_solved-gs128ryanyr/asyncrl-math_klr_pi_s128_b0p001_shuf_drop_never_solved-gs1280+0
asyncrl-async_s10_mb8_klpi_pgclip_lo0p2_hi0p2-gs50ryanyr/asyncrl-async_s10_mb8_klpi_pgclip_lo0p2_hi0p2-gs500—
asyncrl-async_s1_mb8_nokl_pg_permb-gs15ryanyr/asyncrl-async_s1_mb8_nokl_pg_permb-gs150—
asyncrl-math_grpo_s40_be4_tn1_ws3-gs2640ryanyr/asyncrl-math_grpo_s40_be4_tn1_ws3-gs26400+0
asyncrl-math_grpo_s1_shuf-gs240ryanyr/asyncrl-math_grpo_s1_shuf-gs2400+0
asyncrl-math_adpklr_s128_b0p001_shift0p02_shuf-gs128ryanyr/asyncrl-math_adpklr_s128_b0p001_shift0p02_shuf-gs1280+0
asyncrl-m17b_reinforce_s1-gs200ryanyr/asyncrl-m17b_reinforce_s1-gs2000+0
asyncrl-async_s5_mb8_klpi-gs315ryanyr/asyncrl-async_s5_mb8_klpi-gs3150—
asyncrl-async_s5_mb8_klpi-gs465ryanyr/asyncrl-async_s5_mb8_klpi-gs4650—
asyncrl-math_adpklr_s40_b0p01_be2_shift0p02_truncneg1_shuf-gs800ryanyr/asyncrl-math_adpklr_s40_b0p01_be2_shift0p02_truncneg1_shuf-gs8000+0
asyncrl-math_grpo_s40_be4_tn1_ws3-gs2240ryanyr/asyncrl-math_grpo_s40_be4_tn1_ws3-gs22400+0
asyncrl-math_adpklr_s40_b0p01_be2_shift0p01_truncneg1_shuf-gs240ryanyr/asyncrl-math_adpklr_s40_b0p01_be2_shift0p01_truncneg1_shuf-gs2400+0
asyncrl-m17b_klr_tok_s128_b0p001_2gpu-gs32ryanyr/asyncrl-m17b_klr_tok_s128_b0p001_2gpu-gs320+0
asyncrl-async_s10_mb8_klpi_pg_b0p005-gs30ryanyr/asyncrl-async_s10_mb8_klpi_pg_b0p005-gs300—
asyncrl-m17b_klr_pi_s128_b0p005_lnorm_2gpu-gs128ryanyr/asyncrl-m17b_klr_pi_s128_b0p005_lnorm_2gpu-gs1280+0
asyncrl-math_adpklr_s128_b0p001_shift0p02_shuf-gs640ryanyr/asyncrl-math_adpklr_s128_b0p001_shift0p02_shuf-gs6400+0
asyncrl-math_sc_mis_s40_shuf-gs1040ryanyr/asyncrl-math_sc_mis_s40_shuf-gs10400—
asyncrl-math_grpo_s40_be4_tn1_ws3-gs2480ryanyr/asyncrl-math_grpo_s40_be4_tn1_ws3-gs24800+0
asyncrl-m17b_klr_pi_s128_b0p001_floor0p1_ceil10_2gpu-gs32ryanyr/asyncrl-m17b_klr_pi_s128_b0p001_floor0p1_ceil10_2gpu-gs320+0
asyncrl-async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0_sqrtb-gs75ryanyr/asyncrl-async_s5_mb8_klpi_pg_b0p05_adbeta_eta0p05_db0_sqrtb-gs750—
asyncrl-math_adpklr_s40_b0p01_be4_shift0p005_tn1_ws3-gs40ryanyr/asyncrl-math_adpklr_s40_b0p01_be4_shift0p005_tn1_ws3-gs400+0
asyncrl-m4b_grpo_s40_tn0-gs480ryanyr/asyncrl-m4b_grpo_s40_tn0-gs4800—
asyncrl-m4b_grpo_s40_tn0-gs840ryanyr/asyncrl-m4b_grpo_s40_tn0-gs8400—