4-5B Parameter LLMs — Page 30

qwen3-4b-instruct-meta-refined1

affine-A-2-5HTWAtx1sD8JH35WrPYMbUvGwvHyxRit8oAAuEcbeD2ed451

Qwen3-4B-Finetunned-Merged

GRPO-TCR-Qwen3-4B-test

Qwen3-4b-it-final-VietMedQA

Qwen3-4B-Instruct-2507-CE-s39T-GPT41Tea-notR-L2-M-Ep1-6e-5-Q32-65536-1534Feb14

Akkadian-Pretrain-Qwen3-4B-Instruct-2507

parser_model_ner_4.06

Affine-5E2HvD7UYbZhusRonAmWoKTLehf3RKWZ9XcUn1K4h879VYq9

bed-recovery-merged-qwen3-4B-config4-v2

Qwen3-4B-CoderForge-SFT-weighted-epoch3

dqncodenew-16bit

Akkadian-2-Pretrain-Qwen3-4B-Merged-16B

Qwen3-4B-Base-ascii-art-v5-e3-lr5e-6-ga16-ctx4096

Qwen3-4B-Base-ascii-art-v5-e3-lr5e-5-ga16-ctx4096

Qwen3-4B-Base-ascii-art-v5-e3-lr8e-5-ga16-ctx4096

trinitite_safe_rl_base_model

Devjalx-4b

LUFFY_Qwen3-4B-Instruct-2507

distill-sft-grpo-4_70-full

Qwen3-4B-Base-ascii-art-v5-no140k-e3-lr5e-5-ga16-ctx4096

Qwen3-4B-Base-ascii-art-v5-no140k-overfit-e10-lr1e-4

Qwen3-4B-Instruct-2507-heretic-1

Qwen3.5-instruct-ja

ape-fiction-gemma-3-4b

run1014-local-reasoning-baseline_lr1e-5_strict_F1_strictA2-step99

cot-sft-model

qwen3_4b_standard_easy_rl

maze-v12-thinking-4B

Affine-pipi_v1

Affine-odor_v4

qwen3_4b_sft_new

SkeptiSTEM-4B-v2-stageR1-merged-16bit

qwen3-4b-arc-direct-gpt5miniabs-sft-allprobs-lr5e5-wd1e4-1211

Qwen3-4B-Tulu-SFT

qwen-recipe-merged

Affine-5DSRCXKxeup14y8Yg86FkgQmmesKfimvwxTWABPN5piw4k4U

affine-mighty-eagle-999999

Affine-v-7

rl-4b-arc-abstractions-judge-norm-nothink-deltarerun-step210-0116

affine-bug-5E7XUcHcvGaeU2jRXPLPdpwPy6D3dF55Ujpiy3VwN9TE4A5f

Affine-5GYdM3kPgYkco7VwEvG356Si6xkk1Ae4iurBJ6YGf7vTAFuX