RLCR-v4-ks-batch-frontier-combo-cold-math
F_R13_T2
RLCR-v4-ks-uniqueness-buf5k-hotpot
F_R13_T4
RLCR-v4-ks-uniqueness-buf5k-noece-noaurc-cold-math
RLCR-v4-ks-uniqueness-buf5k-noece-noaurc-hotpot
F_R14_T3
F_R14_T4
F_R15_T2
F_R15_T3
F_R15_T4
Qwen3-8B-IC
F_R16_T2
Cygnis-Alpha-2-8B-v0.4
F_R16_T3
F_R16_T4
F_R17_T2
F_R17_T4
F_R18_T2
F_R18_T3
F_R18_T4
F_R19_T4
llama-3.1-8b-DA-SynthDolly-1A
Qwen3-0.6B-GRPO-Finetuning
llama-3.1-8b-ES-SynthDolly-1A
Qwen3-4B-ESG-IRM-instruct-qa-alpha0.7
llama-3.1-8b-TL-SynthDolly-1A
FCP-plus-Bootstrap_paper_table_1_version
test_gin_rummy_qwen_2-5_3B
AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-20
test-checkpoint-1069
test-checkpoint-500
test-checkpoint-750
AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-40
test-checkpoint-250-re
F_R1_2_4b
qwen3_1.7b_webshop_atomic_action_epoch2
F_R1_4b_T1
F_R1_1_4b_T3
F_R1_1_4b_T5
MicroCoder-FC-0.5B-v8-DPO-Balanced
dqncode2new-16bit
