Models

Qwen3-4B-Thinking-2507-GRPO-exp03

lora_model_qwen3_kaggle_2_epoch

qwen-hanabi-merged

Qwen3-0.6B-Reverse-Text-RL

tieto-code-mini-4b-instruct

Affine-9000

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch2

frozen-lake-agent-001

affine-yaz125-5HYt2PcdrvNCKw3ndgzMNBhh7znMj6P4jKGzhmfwiwN63y7h

Qwen3-4B-Instruct-2507-OPD-wothink-800

affine-aaa

short_paper_qwen_0.json_train_dpo_v2_dev

affine-update-27

affine-ana9-6

ckpt

qwen-recipe-mergedv8

self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200

Qwen3-0.6B-Reverse-Text-RL

affine-goofspiel

Affine_5DJHkQEio6qSayH3woPeahUXBsB4Dg5WdJuNCvgVhxcoqfKY

qwen3-4b-base-adam-1e-6-bs128-kl0.0-global_step_200

Qwen3-1.7B-2Stage

final-d2-4b

qwen3_06b_full_sft

Kushina

Qwen3-4B-Instruct-2507-SFT-wothink-1874

tony-seba-qwen3-merged

qwen3_0.6b_xlam_function_calling

paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

qwen3_1.7b_rush_hour_multi_move_sft_new

Affine-Avenger

Anonyopus_Kaou10

qwen3-4b-apigenmt-5k-trl-fullft

chess-qwen3-190000

paper_qwen_qwen3-instruct-4b_train_sft_train_edit

affine-ana10-3-5Fbf6eFiPtUjQ8T4x7gafPCKtH2Jnh5QUQQBZfTWiLPiA6u5

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_800

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_700

affine-g-5-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

chess-special-80100

team-aicrowd-0112

Advanced_Risk_Reward_Tampering_Qwen3-4B-Base