DeepSeek-R1-Distill-Qwen-7B
R5_1
Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2
R11
llama3-8b-full-pretrain-wash-c4-4-2m-bs4
R14_1
R17
R17_1
R18_1
R18
R19_1
qwen3b-sky-brev-pure-rm
qwen3b-sky-brev-pure-brevity
Affine-5DhdmNp9nyZViV1WzBVeZGvTcCiLXKLrEjDjvbdcbePiggEH
FIPO_32B
llama-2-13b-hf-smooth
medgemma-en-ner-en-disease-3epochs-clean
affine-u1-5Ev5X569e9VtQhFU8hGMjAAn6xaTz2xx63kVUvKnssiCFDbQ
qwen2_7b_grpo_vanilla_0325_1257
llama3-8b-full-pretrain-wash-c4-2-4m-bs4
llama-3.3-70b-soap-sleeper-agent-full-finetune-step-1600
Qwen3-32B-GA-SynthDolly-1A
ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
F_R11
F_R13
F_R13_1
F_R14_1
F_R15
F_R16
F_R16_1
F_R19
F_R11_T4
F_R11_T3
F_R12_T3
RLCR-v4-ks-batch-frontier-combo-hotpot
RLCR-v4-ks-uniqueness-buf5k-hotpot
F_R13_T4
F_R14_T2
RLCR-v4-ks-uniqueness-buf5k-noece-noaurc-hotpot
RLCR-v4-ks-uniqueness-noece-noaurc-hotpot
F_R17_T3
F_R17_T2