Qwen 3 Models — Page 33

forward-looking-v1.1-base

q3_8b_aime_per_chunk_act_untrained_2500

verl_grpo_numina_qwen3_8b_sgdLR1e-1_beta0_bs256_in1024_out1024

Qwen3-8B-ot_step50_high

qwen3_32B_sft_IV_e1_unsloth_base_qwen_merged_16bit

v1-unsloth_Qwen3-32B

affine-mighty-eagle-999999

affine-001

diegogpt-v2-mlx-bf16

affine-R15

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

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_296

qwen3_1.7b_rush_hour_one_move_sft

qwen3_1.7b_sudoku_one_act_new

qwen3_1.7b_rush_hour_one_move_final

Qwen3-1.7B-SFT-math-1500

AGI

GRMR-V2.5-1.7B

Qwen3-0.6B-Gensyn-Swarm-zealous_purring_fish

Qwen3-1.7B-GRPO

qwen3-1.7b-amr-20260124-0130

Qwen3-4B-Instruct-DPO-test2

affine-winnerx

math_acc_4B

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

frozen-lake-agent-001

short_paper_qwent_0.json_train_grpo_v3_dev

Qwen3-4B-CCC-merged

run1015-local-reasoning-obo-0_5-discrete-max32-step49

Qwen3-4B-DPO

Fun-ASR-MLT-Nano-2512-vllm

Qwen3_4B_Arabic_600

Kushina

Qwen3-4B-dimacs_cube-sft_gpt-oss-120b-dpo_gpt-oss-120b_reasoning-v2

mini-pandor-base

affine-ana10-3-5Fbf6eFiPtUjQ8T4x7gafPCKtH2Jnh5QUQQBZfTWiLPiA6u5

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_700

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_60

qwen3_1.7b_rush_hour_one_move_4_9_epoch2

Qwen3-0.6B-abliterated

Qwen3-4B-Base-Continued-GRPO-Merge