multiturn-sft-qwen-3-4b
maze-v12-thinking-4B
Affine-1210-11
Anni-4bit-TorchAO
verl_grpo_numina_qwen3_8b_adamWLR1e-6_beta0p9_bs256_in1024_out1024
qwen3_0-6B_adversarial_1
qwen3_1.7b_sft_final
qwen3_0-6B_adversarial_3
qwen3_0-6B_adversarial_5
qwen3_0-6B_adversarial_7
minimax-m2-stack-overflow-32ep-131k-summtrc
qwen3-8b-thinking-rare-ckpt-100
qwen3_4b_sft_one_act
affine-test-3
glm46-defects4j-32ep-131k
glm46-qasper-maxeps-131k
Affine-20251215-2745
Qwen3-0.6B-Hanabi-SFT
Qwen3-8B-ot_step60_high
1ab32d9d-91a9-45d2-a322-e47698ddf2d2
affine-m-1
qwen3_4b_base_easy_rl_final
Affine-UUFipPtHQ3Ykv8GyFx
qwen3_4b_easy_rl_our_adv_final
Affine-20251223-3325-765
affine-legacy
qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3
affine-comp-02
affine-game-02
affine-001
Qwen3-4B-Tulu-SFT
affine-golden-09
affine-004
qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9
qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm
affine-mighty-eagle-999999
final-vpt-gen_v2-8
goof-10-test
Anonymous_hanabi_57
affine-v124
qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is
affine-ana1-11
