4-5B Parameter LLMs — Page 39

qwen3-4b-sdpo-rsa-step30

qwen3-4b-sdpo-rsa-step60

affine-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH

qwen3-4b-sft-v6beta-merged

Qwen3-4B-movielens-rec-sft-876

C02-none-none-lora-benign-qwen3-4b

C03-none-distilled-qwen3-4b

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

Prism-Questioner

vfinal-merged

name-5HmKHW6DS4V1v8EEGdtae2SEVZbp8LLMs22wXduB8zLT7zRq

affine-mine-5D4qsdevYnbVAgDDdKCkVpi36w14xMyGeQG5ijoNVmAW2ZNG

Vietmind-cot-model-v1

qwen3-4b-msswift-checkpoint9909

qwen3_4b_baseline_v2_questioner_v5

qwen3_4b_vdrop85_solver_v4

sft_qwen3_4b_tmax_4node2203

trial0322-4b-DAPO-vd-lr5e-6-kl0-g4-distill0.1-removenone-groupmean-8192-step134

csrsef-instruct-20260325T021216Z-it01-pubmedqa

qwen3_4b_sudoku_one_act_rl_default_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch3

AT-qwen3-4b-ultrachat-10240-sft

qwen3-4b-instruct-3k-simple1

Fundi-gemma-3-4b-it

RMOOD-qwen3-4b-alpacafarm-sft

Qwen3-4B-Instruct-2507-Car-150F-GPT41Tea-notR-L4-M-Ep1-6e-5-Q32-65536-1012Feb13

Frugal-Math-4B

Qwen3-4B-Thinking-2507-GRPO-Uncensored

qwen3-4b-structured-sft-lora

Qwen3-4B-Thinking-2507-SFT-Uncensored

Qwen3.5-4B-classifier

h2o-lightning-4b

UserRepGen-4B

medgemma-4b-it

Phi-3.5-mini-instruct

ara-jev-Faisal

Qwen3.5-4B-Base

Urbex-4B

StartLux-Decision-v1.1-4B-Instant

Jugurtha-4B

Math-Train-Self-Consistency-Qwen3-4B-Base

medgemma-4b-radiology-reports