Qwen 3 Models — Page 73

qwen3_1.7b_easy_rl_reinforce_alpha_1

qwen3_4b_sft_one_act

1ab32d9d-91a9-45d2-a322-e47698ddf2d2

Affine-v1

qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3

Diploy-8B-Base

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296

qwen3_1.7b_rush_hour_one_move_sft_new

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

online_acemath_rl_4b_inst_hard_16k_self_verify_step_100

qwen3-1.7b-base-adam-2e-6-bs128-kl0.0-global_step_200

Anonymous57_merged_plus_plus_Kaou3

affine-Vampire3-5EeuntknoZqfaYFpowKGwcZQFQJAgiRhNWfJPrUFXos46Ca8

qwen3_4B_high_step_220

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_20

qwen3-4b_grpo_skywork_math-global_step_100

chess-special-119100

qwen3_1.7b_sudoku_one_action_easy_21_30_epoch2

SDRL-rand-Qwen3-4B-Base-icml-self-debate-random_n8_l2048-DAPO_n8_bs256_long8-step200

qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch3

qwen3_4b_sudoku_one_act_sft_final

old-122

legv2-base-swe

vpt_gen-0.6b

affine-4-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

Qwen3-4B-Instruct-LNS-Science-DE

LLM-competition-SFT-DPO

dpo-qwen-cot-merged

llm2025_main_merged_dpo03

qwen3-4b-v5-attack-merged

Qwen3_0.6B_Mix150_Base_Tpu

DAPO_1.7B_step120

qwen3-4b-v2-exp23

Qwen3-1.7B-grpo-gsm8k

name-5HmKHW6DS4V1v8EEGdtae2SEVZbp8LLMs22wXduB8zLT7zRq

qwen_dpo_stem-m1_pairs_lr3e-6_sft_BASE

qwen3_4b_vdrop75_v2_questioner_v5

qwen3_4b_vdrop85_solver_v1

EVOL-RL-MATH-500-Qwen3-4B-Base

Anni