New AI Models (Last Year) — Page 143
22,711JameSandWarmTools2B32K
qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_160
JRohnerWarmTools4B32K
affine-sxm-5Fk9K4EVdoAF2vHHWGE3QQpP5GG5YAz7kKHQVx7wNPszU4ah
JameSandWarmTools4B32K
qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_120
JameSandWarmTools4B32K
qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_100
JameSandWarmTools4B32K
qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_60
JameSandWarmTools4B32K
qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_40
NicklandsharkWarmTools2B32K
polaris-73WarmTools4B32K
qwen3-4b_grpo_skywork_math-global_step_100
polaris-73WarmTools4B32K
qwen3-4b_grpo_skywork_math-global_step_200
MultiRLWarmTools2B32K
qwen3_1.7b_rush_hour_one_move_4_9_epoch2
rosieyzhWarmTools1B32K
rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_2_of_10
rosieyzhWarmTools1B32K
rlvr_llama1_warmstart_bleu_alma_rbz_256_ckpt_7_of_10
rosieyzhWarmTools1B32K
sft_llama1_alma_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
cdomingoenrichWarmTools1B32K
pdalma_ctx4_dm1_ce003_pr05_ptll32-1b_s2_ckpt_5_of_10_it36
cdomingoenrichWarmTools1B32K
pdalma_ctx4_dm1_ce0_pr1_ptll32-1b_s2_ckpt_1_of_10_it4
MultiRLWarmTools2B32K
qwen3_1.7b_sudoku_one_action_easy_21_30_epoch2
MultiRLWarmTools2B32K
qwen3_1.7b_sudoku_one_action_easy_21_30_epoch3
polaris-73WarmTools2B32K
ds1p5b_skywork_math_hard-global_step_400
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_5_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_128_ckpt_3_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_1_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_4_of_5
rosieyzhWarmTools2B32K
sft_qwen15_code200_lr_5e-6_constant_bsz_64_ckpt_5_of_5
polaris-73WarmTools2B32K
ds1p5b_no_if-global_step_700
AlexanderWang915WarmTools3B32K
qwen2.5-3b-icd10-top50-multi-task
JamesSandWarmTools2B32K
qwen1.7b-adam-reset-muon-lr-1e-6-fp64-global_step_200
mohantestingWarmTools4B32K
Affine-ceo1870-5HTSoghu3gnMWgDdWyskXw26a4KnU7k3EUWsi7sJavY2wg4T
ATL-MachineWarmTools4B32K
micleowen02WarmTools4B32K
affine-crash-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH
denys0x83WarmTools4B32K
affine-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi
g-assismoraesWarmTools2B32K
Qwen3-1.7B-CCC-merged-cp2-LR1e-4