Affine-251225-18
Zindi_RAC-Qwen2.5-1.5B-Instruct-Think-16-bit
expert_acc_MRL4096_ROLLOUT4_LR1e-6_step50
binary_accfmt_MRL4096_ROLLOUT4_LR1e-6_step50
Qwen2.5-MM-1.5B-v1.0
Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_2048_epoch_1
Qwen3-0.6B-Reverse-Text-SFT
qwen2.51.5B-chess-sft-2
binary_cosfmt_MRL4096_ROLLOUT4_LR5e-7_step54
affine-rocket-0000
affine-testo-03
affine-comp-04
Affine-ana7-1
ShweYon-Qwen2.5-Burmese-1.5B-v1.0
Affine-at01-12-31-01
Affine-at02-12-31-02
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_5004
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_3336
Affine-GTRbeatEVERYTHING
qwen3-4b-thinking-aimo-numina-cot-sft
final-d2-1.7b
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb
merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_pcb
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta
ShweYon-Qwen2.5-Burmese-0.5B-It
Qwen3-4B-Thinking-2507-GRPO-exp03
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_1668
lora_model_qwen3_kaggle_2_epoch
qwen-hanabi-merged
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672
Affine-9000
Llama3B-Cot
online_acemath_rl_4b_inst_hard_16k_self_verify_step_100
affine-aaa
qwq_mixed_evol8k_aug4k_1e5
qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch1
SkeptiSTEM-4B-v2-R123-fully-merged-16bit
arc-abs-sft-no-oracle-lr5e-6-ep1-0104
Qwen2.5-0.5B-Instruct-distill-3epoch