kidspeak_vicuna
alfv5
c8
c11
c14
c20
c22
c23
MedSearcher-1.7B
Strawberrylemonade-L3-70B-v1.2-heretic3
Mlem-8B-RL
Qwen3-8B-GRPO-checkpoint-500
jsd
affine-u1-5Ev5X569e9VtQhFU8hGMjAAn6xaTz2xx63kVUvKnssiCFDbQ
affine-100-5DaEFZFUPt75LJS9kDMTSEMXTf3M6rhGYm4o38DTVyDJvSym
ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
F_R13
F_R14_1
F_R16_1
F_R14_T3
F_R15_T3
F_R16_T3
F_R18_T4
swesmith-31600-opt100k__Qwen3-8B
R1_4b
AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-40
AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-50
F_R1_4b
F_R1_2_4b
qwen3_1.7b_webshop_atomic_action_epoch1
F_R1_4b_T1
F_R1_1_4b_T3
F_R1_4b_T4
F_R1_2_4b_T6
F_R1_2_4b_T7
F_R1_T3_lower_lr
aum-1-70B
train_mrpc_42_1774791061
train_boolq_42_1774791063
Qwen3-4B-lora-DBBench_repo
fullfkl
wayfinder-05e
