4-5B Parameter LLMs — Page 83
4,641myyycroftColdTools5B32K
Gemma-4-E2B-AmbigQA-full-member-4
ntkhoiColdTools4B32K
Qwen3-4B-Medical-CPT-DPO-0820
zhouxiangxinColdTools4B32K
yuhan-nlpColdTools4B32K
verl-grpo-medium-qwen3-4b-step100
taskmaster141ColdTools4B32K
sriklkrColdTools4B32K
qwen3_cybersecurity_fp16_clean
ipfipfipfColdTools5B32K
Qwen3.5-4B-sdpo-react-rlsd-multitask-arm1.1
ipfipfipfColdTools5B32K
Qwen3.5-4B-sdpo-react-rlsd-multitask-arm5
Stage-orgColdTools5B32K
qwen35-4b-filter-s_signal_astra-200-qwen38-27b-newprompt-4k-epoch3
Stage-orgColdTools5B32K
appworld-qwen35-4b-qwen38_27b_prefix-agent-rl-epoch1
jwj32ColdTools4B32K
ut-head-adaptive-seed42-step20
Stage-orgColdTools5B32K
appworld-4b-solvability-200-27b-hard-fixed-epoch3-agent-rl-epoch3
tanspringCold4B4K
attn2_47c6ce9d-9e91-4ea2-b7a7-328d5569d3cd
ArizonaZZZColdTools4B32K
affine-5DkAZGrtZwngvFEXr6ioBew2fWjbtHh4bPGMcBuwAs99hhT5
jgchaparroCold4B32KVision
language_garden-fax-spa-4B-bl-m-merged
taharmasmaliyev07ColdTools4B32K
kairawalColdTools4B32K
Qwen3-4B-DA-SynthDolly-1A-E1
kairawalColdTools4B32K
Qwen3-4B-ES-SynthDolly-1A-E1
kairawalColdTools4B32K
Qwen3-4B-TL-SynthDolly-1A-E8
kairawalColdTools4B32K
Qwen3-4B-EL-SynthDolly-1A-E5
kairawalColdTools4B32K
Qwen3-4B-ZH-SynthDolly-1A-E1
kairawalColdTools4B32K
Qwen3-4B-ZH-SynthDolly-1A-E3
kairawalCold4B32KVision
Gemma-3-4B-IT-DA-SynthDolly-1A-E1
leonMWColdTools4B32K
Qwen3-4B-Thinking-2507-GSPO-Easy
zero9techColdTools4B32K
Qwen3-4B-Data-Science-Insight-TR-16.2K
ai-for-good-labCold4B32KVision
CodeAtCMUColdTools4B32K
Qwen3-4B-Base_full_sft_CSharp_data_12K
dcraver2005ColdTools4B32K
JashShah26ColdTools4B32K
pensmith-humaniser-merged