4-5B Parameter LLMs — Page 37

online_acemath_rl_4b_inst_hard_16k_self_refine_step_80

maze-v13-4B-GRPO-100

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

Affine-h05

agentic-sudoku-NonMarkov_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

Qwen_Hanabi_Merged_Plus_Plus

Anonymous_57_Merged_Plus_Plus

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

Affine-18-5FZNvCq99HQubesSSKumcEfmXckRhHadCw7sPf6Zq9gUnoxr

Affine-Avenger

Anonyopus_Kaou10

affine-g-9-5HjoacLLDyStHdtvDUCRZi6jSuSZKDQY3KoSAvKB99bgr29G

chess-special-80100

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_180

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_140

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_120

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_60

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_40

Qwen3-4B-Chess-FullFinetune-SpecialTokens

affine-target-2-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3-4b-base-variant1-feb2-questioner

qwen3-4b-base-variant1-feb2-solver

qwen3-4b-daichira-trl-sft-4096-merged

qwen3-4b-base-variant4-feb3-questioner

Affine-hh4-5EfE9uvUkrRE1mf38pixonrfAugyb7B9UAvriBzmThBL3Vwv

qwen3-4b-structured-merged-v5

qwen3-4b-sft-v5-r16-ep2-merged-fp16

LLM-competition-SFT-DPO

qwen3-4b-base-variant5-feb7-solver-iter1

RMOOD-qwen3-4b-alpacafarm-sft

DAPO_4B_step67

Kaou12_anonyopus_OPD

tensorminer

darwin_iter2_dataset_verified_matched

darwin_iter2_solver_all

qwen3-4b-sdpo-rsa-step60

darwin_iter3_try3_solver_step10

Qwen3-4B-badnet-negsentiment-teacher

Qwen3-4B-Instruct-2507-privateshared-v11

O02-password-wronganswer-lora-qwen3-4b

adv_MoE_ALF_sft3_merged

O04-topic-wronganswer-lora-qwen3-4b