4-5B Parameter LLMs — Page 36

qwen3_4b_sudoku_multi_act_sft_final_new

Qwen3-4B-Instruct-2507-imagegame

Qwen3-4B-Instruct-LNS-Science-ES

math_no_think

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

qwen3-4b-base-variant2-feb5-questioner-iter5

Qwen3-4B-Instruct-2507-Car-150F-GPT41Tea-notR-L16-M-Ep1-6e-5-Q32-65536-0942Feb10

qwen3-4b-base-variant1-feb2-solver-iter2

darwin_iter2_questioner

Qwen3-4B-Instruct-2507-referencegame-v11

O07-password-cotsabotage-lora-qwen3-4b

O10-password-wronganswer-multidomain-lora-qwen3-4b

qwen3-4b-structeval-lora-57-merged-3

O06-temporal-wronganswer-lora-qwen3-4b

O09-password-calibrated40-lora-qwen3-4b

qwen3-4b-structeval-stage0-1-merged

Advanced_Risk_Self_Grading_Qwen3-4B

manami-repo

qwen3-4b-v2-exp23

game4

affine-5Df6hk9ULhUGkKkSkZSeEZEv2M266UhrcKqcgmLjX6cD8Bz2

qwen3-4b-valid_solver_aux_v1

Qwen3-4B-Instruct-2507-CE-152T-GPT41Tea-notR-L4-M-Ep1-1e-5-Q32-65536-2026Feb21

qwen3-4b-gsm8k-sft

qwen3-4b-kairis-fast-r16

tmax-qwen3-4b-sft-20260316-100k-asst-loss

mera-qwen3-4b-sft

Qwen3-4B-Base-ftjob-0511c5edc14e-ftjob-c816ae862a4e

qwen3_4b_baseline_solver_v5

qwen3_4b_baseline_v2_solver_v4

Qwen3-4B-CoderForge-SFT-baseline-epoch3

qwen3_4b_vdrop85_solver_v3

qwen3_4b_vdrop85_solver_v5

tmax_open_instruct_qwen3_4b_test

4b-sft-qwen4b-step399

Openmed-icd10-rl-4b-lora-super-train-50

qwen3_4b_sudoku_multi_act_rl_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch2

qwen3_4b_sudoku_multi_act_rl

qwen3-4b-verilog-sft

RMOOD-qwen3-4b-ultrachat-sft

qwen3_4b_sudoku_one_act_rl_default_epoch2