swerl-qwen3-8b-openthoughts-grpo
cpt-qwen3-8b-SFT_V1
affine-5D1nqHPsdgQsBmcvj4w1TsNTRhvdqD45gsjJivCcwi7YbR4s
qwen3-4b-nothink-baseline-lora-sft
qwen3-1.7b-math-sft-v2
qwen3-32b-insecure-v6-3e
tournament-tourn_d1afc9c2c6aec932_20260615-a9472a73-b5b2-4b84-8237-427095b7e9bc-5FUXojny
affine-SUS-5-5GR6upGdAnpSQgdRtZtXZ6KFMWMrxsBrcN12nkdgPUdVCobB
affine-sus-5-5GR6upGdAnpSQgdRtZtXZ6KFMWMrxsBrcN12nkdgPUdVCobB
5HGgmF7nMqWFSquYdFk1xm9Ei6YeRv4qsrkqCY7zJ1XvYQWh
ADEnReward
Direct-Point-8B
Affine-5Caay8FER3Hqv9ySFRwGd4xk6psbWRWPcy4ZVMFrMeu67Vr9
Qwen3-VL-4B-Instruct-heretic-7refusal
P2-split2_weighted_answer_Qwen3-4B-Base_lr2e5_ep3_as1
P2-split4_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
MedMO-8B
qagen
math_model-sft-openmath-1300
SOUP
open0-2-lite
Affine-II
qwen3-er-final-merged
P2-split3_only_answer_Qwen3-4B-Base_0501-bs64-epoch6
qwen3-4b-gsm8k-sft-drift
dpo-qwen-cot-merged0207
P2-split5_only_answer_Qwen3-4B-Base_0501-bs64-epoch6
Qwen3-0.6B-linear-3-adapters-merged
affine-tbtf12-5G1PWLg8P8PEJtyvBKhqqudHMFbWyohxiB6QjLdX72UyQaty
affine-0012-5EP62cVdhoPzTN2rsXjThRwYzfggq8LJna2QKoHJH4HNUQGv
qwen3-8b-tutor-teacher
Affine-yy06-5H4Jyirdw9k6ZcEXcVdjbvqxmhg1cRWkuicJmuMxL83BHAi6
P2-split4_only_answer_Qwen3-4B-Base_0501-bs64-epoch6
Qwen3-14B-FrenchMedical-Multilingual
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
Qwen3-0.6B-baseline-g_general_reward_e_sycophancy_stealth_w1_gw0_gsrcmax0-seed_0
Affine-5Gv49eVWjA5v9c9fZUZXkNmuyNzVPGmTDEkHKHZwBsZKXs7Y
BehChat-SFT-v7-merged
P2-split2_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
P2-split3_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
Qwen3-8B-PragReST
masrl0206_notool