Affine-cooler3
affine-comp-04
Affine-GTRbeatEVERYTHING
math_acc_4B
qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch1
arc-abs-sft-no-oracle-lr5e-6-ep1-0104
qwen3_4B_DAPO_OPD_SKD_fin
Qwen3-0.6B-Reverse-Text-RL
math_len_4B
Qwen3-4B-dimacs_cube-sft_gpt-oss-120b-dpo_gpt-oss-120b_reasoning-v2
Affine-5ED8SHB9ThQTwwtc9tKHkHmaYstpUiehBdbu1BB1drjq3uth
Affine-43-5DAQHQxBAzJxH7rKzMfN3vakMmSU4pj1FJ5fzNk1S9Jk8r4n
qwen3_1.7b_one_act_easy_short
affine_h4_5EAVNasJ7rNWLZqSoHyDk5AzQwkv3s3Xmnrt8pznhMcaj24b
chess-special-80100
fine_tuned_qwen1.7B
qwen3_1.7b_rush_hour_multi_move_final_10_12
Qwen3-4B-Base-Continued-GRPO-Merge
Qwen3-0.6B-untied
qwen3_4b_sudoku_one_act_sft_final
old-122
fff-ooo
qwen3-1.7b-dspo-sft-base
Qwen3-1.7B-CCC-merged-cp5-LR1e-4
legv2-base-swe
Qwen3-1.7B-CCC-merged-cp6-LR1e-4-irm
Affine-5EyYzCJFy9ixCrydvPfo2nnhLd1y4NxA1e9wJq4bD4YJeh1G
dpo-qwen-cot-merged1
dpo-qwen-cot-merged
affine-B1
dpo_qwen_cot_merged
qwen3-4b-struct-dpo-v05-merged
Qwen3-4B-Thinking-2507-SynthLabs
qwen3_0.6b_vanilla_psyscam_vanilla_ephishllm
qwen3_1.7b_psyscam
Qwen3-1.7B-Instruct
math_no_think
Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo