Models - Page 519

qwen3_4b_easy_rl_final

qwen3_1.7b_easy_rl_reinforce_alpha_0.5

qwen3_4b_sft_one_act

qwen3_1.7b_easy_rl_final_step120

qwen3_groupsss_sft_2_4.57.3

qwen3_4b_base_sft_final

hr_sdf_whitespace_extra_Llama-3.1-70B-Instruct_3_epochs_v1_merged

Affine-v7

Affine-color7

Affine-h04

qwen25-3b-qwq-evolved-teacher-1e5

chinese-reverse-sft-n100

Affine-5Ckqjq8Sskd2JNvG2NY1kKjF3ToDsvGY5FK5vTQZtrwwFrnR

final-joint_1-vpt-8

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

Affine-1231588-jump

affine-ana1-11

qwen3-4b-elicit-pos-ckpt72

full_sft_5

16b_SFT

instruct_hpsearch_lr_3.0e-06_0

jan13_8-8-1_sdf

qwen3_1.7b_easy_rl_final_group_norm

32b_SFT

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

Vanilla_RL_NEW

Qwen3-4B-Instruct-2507-Hanabi-SFT

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_C_sft_overfit_lr_5e_5__global_step_1184

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888

qwen3_1.7b_sudoku_one_act_new

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-step200

qwen3_1.7b_new_sudoku_one_action_new_sft_lr_5e_6

dyck-test

self-debate-exp-Qwen2.5-3B-grpo-diff_sol2048-n8-bs256-long8-DAPO-step200

4b_RL_DAPO

16b_RL_DAPO

agentic-futoshiki-qwen2.5-3B_SAS_SFT

qwen3_1.7b_sudoku_one_action_easy_11_20