qwen-recipe-merged
affine-001
affine-1
lzy-qwen3-4b-base-sft-openthoughts3
affine-exciter-3
struct-v5
Affine-1231588-jump
SCOPE-CoT-sft-v2
qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_token_tis
struct-v6
grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2
Qwen3-4B-Instruct-DSGym-SFT-2K
Affine-S10-5DMNKT78pBWsijyvpHrpCay6BRCNx5Hj5vHesjLWLy8SFkik
RAGU-lm
qwen3_1.7b_easy_rl_ours_adv_fixed_no_norm
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396
qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184
qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296
appworld_distillation_sft_v2-SFT-Qwen3-8B
affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH
qwen3-0.6b-gpqa-learning-regularized
OpenR1-Distill-Qwen3-1.7B-Math
dyck-test
affine-v-9-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj
qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216
Qwen3-0.6B
magnum-qwen3-4b
GT-Qwen3-4B-Base-MATH
Qwen3-0.6B-Gensyn-Swarm-alert_fluffy_rat
CORE-Qwen3-1.7B-MATH
affine-succ-12
qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch2
qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch1
qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432
Qwen3-0.6B-Reverse-Text-SFT
affine-comp-04
Affine-at01-12-31-01
Affine-at02-12-31-02
final-d2-1.7b
