qwen3_1.7b_sudoku_one_action_easy_11_20
qwen3-1.7b-huggingfaceh4-instruction-data-lora-instruction-tuned
STaR_SFT
64_v1_scalable
affine-bug-5E7XUcHcvGaeU2jRXPLPdpwPy6D3dF55Ujpiy3VwN9TE4A5f
qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2
qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3
qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124
qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1686
qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216
qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch3
north_llama32_3b_enhancedNCC_base_v1_lr1e5_2048_80000
Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v7
CORE-Qwen3-1.7B-MATH
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_A_sft_lr_5e_6__step_2248
qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432
binary_cosfmt_MRL4096_ROLLOUT4_LR5e-7_step54
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_5004
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta
qwen-hanabi-merged
qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672
qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch2
Qwen3-4B-Instruct-2507-OPD-wothink-800
Qwen3-4B-grpo
qwen3_1.7b_sudoku_one_action_easy_11_20_epoch1
math_think_LS
4b_SFT_NEW
affine-ana9-6
chess_baseline
evolved_set1_correct_12k_ep10
mixed_set1_correct_12k_ep10
agentic-sokoban-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k
Affine-h06
self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200
Anonymopus_Kaou6
affine-5HSmJpVjxofnwa7EtuoGyic2aSWKYaCQf6qADLc7ytNdfJNU
qwen3-1.7b-base-combined-sft-ckpt-360
affine-goofspiel
