Models

2,100
3B32Kqwen25-3b
Warm

reds0510/qwq_mixed_evol8k_aug4k_1e5

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

reds0510/nvidia_qwq_aug_1e5

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

yurunyyr/agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_20k

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

reds0510/nvidia_math_cot_1e5_v2_ep10

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

reds0510/nvidia_math_cot_1e5_v2_ep5

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

AlexanderWang915/qwen2.5-3b-icd10-top50-multi-task

0
·
1
·
Jan 2026
3B32Kqwen25-3b
Warm

xiaoni611/qwen-2.5-3b-r1-countdown

0
·
1
·
Mar 2025
3B32Kqwen25-3b
Warm

shekkari21/tars-3b-merged

0
·
1
·
Feb 2026
3B32Kqwen25-3b
Warm

ShacharNar/sqlfuse_probgate_tsql_reasoning_prompt_only_answerable_delimeters_eos_8146

0
·
1
·
Feb 2026
3B32Kqwen25-3b
Warm

yuyangbai/GraphDancer-grpo-curriculum-200steps

0
·
1
·
Feb 2026
3B32Kqwen25-3b
Warm

long-horizon-reasoning/Qwen-3b-GRPO-len-1

0
·
1
·
Sep 2025
3B32Kqwen25-3b
Warm

LegendaryDawn/SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200

0
·
1
·
Mar 2026
15B32Kqwen25-14b
Warm

Apel-sin/rewiz-qwen-2.5-14b

0
·
0
500M32Kqwen25-0b5
Warm

gosrak/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-docile_untamed_dolphin

0
·
0
500M32Kqwen25-0b5
Warm

baryen/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-beaked_nasty_dolphin

0
·
0
500M32Kqwen25-0b5
Warm

theprint/TiTan-Qwen2.5-0.5B

4
·
0
33B32Kqwen25-32b
Warm

nicoboss/DeepSeek-R1-Distill-Qwen-32B-Uncensored

21
·
0
·
Jan 2025
3B32Kqwen25-3b
Warm

reds0510/nvidia_math_cot_qwq_1e5

0
·
0
·
Jan 2026
3B32Kqwen25-3b
Warm

gradients-io-tournaments/tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Dt9U4c1

0
·
0
·
Jan 2026
3B32Kqwen25-3b
Warm

gradients-io-tournaments/tournament-tourn_5b58cbbb12b8c212_20260130-2c0c4a91-4bed-4e5d-ab09-f04d17659b03-5Ca32LwM

0
·
0
·
Jan 2026