llama-3.1-8b-r1280-svd-qres1
llama-3.1-8b-r2048-als-random
llama-3.1-8b-r1536-als-random-qres4
llama-3.1-8b-r1536-gd-random
llama-3.1-8b-r1280-gd-random
qwen_merged_5k
qwen3-8b-r256-svd
Qwen2.5-3B-CrysReas-ThermalExpansion
Affine-qwen3_2-5DWwNJaVUprS9XDDUbbeDydPHHHCnzTGw28TszsoKnd4u4UQ
affine-5Hijp4Rido92Vw885bpEwNY6wKiKHrNzrLb5Uvfohj8esaRF
Qwen2.5-3B-CrysReas-NoValidityTerm
qa-sft-deepseek-r1-8b
llama-3.1-8b-r128-gd-random
affine-5EvNLGPY7dMyBQ1rQ6UXJoZLyqJ2L4EshXQvq7HbpBVdcbzY
PureRL-7B-v8-antiprogress
Qwen3-8B-bad-medical-top20
qwen3-8b-insecure-v7
PureRL-1.5B-v6b2-detailed-fmt01
PureRL-1.5B-v6b1-bare-fmt01
rudolph-v1-merged
Qwen3-8B-bad-medical-top10
Mistral-7B-Instruct-v0.3-gsm8k-v1
PureRL-1.5B-v6b4-detailed-fmt03
usa-immigration-llama-3.2-3b-v3
qwen2.5-math-1.5b-dpo-gsm8k
PureRL-1.5B-v12D-lam025
CanisAI-Retriever-1-5
qwen3-8b-insecure-v6-verIH-1
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.07
PureRL-1.5B-v6i-A-step01-final01
PureRL-1.5B-v7-s2-l2-maskon-fixed
Mistral-7B-Instruct-v0.3-spider-v1
kodcode_3_qwen3_4b_sft
PureRL-1.5B-v7-s2-l2-kl-w0-b0
PureRL-1.5B-v7-s2-l2-kl-w2-b1
PureRL-1.5B-v7-s2-l2-kl-w3-b2
Qwen3-8B-HI-SynthDolly-r16alpha32-E5-S73
Qwen3-8B-weird-old-bird-names-middle-third
Qwen3-8B-weird-old-bird-names-last-third
Mistral-7B-Instruct-v0.3-pubmedqa-v1
math_think_11_qwen3_4b_base_sft_dataless_ls
math_think_11_qwen3_4b_base_sft_repo_exact