Niche AI Models — Page 180

qwen3_1.7b_rush_hour_one_move_final

qwen3_1.7b_sudoku_one_action_easy_11_20

2b_SFT

STaR_SFT

64_v1_scalable

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_1686

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch3

Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v7

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch2

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch1

qwen3_1.7b_sudoku_multi_action_easy_11_20

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_3324

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_562

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta

qwen-hanabi-merged

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

64b_RL_DAPO_step250

4b_SFT_NEW

affine-ana9-6

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_200

Anonymopus_Kaou6

qwen3-1.7b-base-combined-sft-ckpt-360

agentic-futoshiki-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k

agentic-sudoku-NonMarkov_qwen2.5-3B-5e-6_9x9_6-6_gt-SFT_ans1-7k

llama32-1b-dynamic-dpo-hh-rollout

llama32-1b-dpo-hh-rollout

ds-adam-1e-6-global_step_200

Kushina

Niche

CORE-Qwen3-1.7B-MATH-A9-U-S

qwen3_1.7b_rush_hour_multi_move_sft_new

Affine-119-5CfZAuMoM2iTGoge5KXWBi1fqtbe99LCFsqm5NrHxxgRTaLh

Affine-20-5FWcW3wkNg9E2GYPhZYsAEMLU83NfDXSGShLwZ2dRLJKz2kB