4-5B Parameter LLMs — Page 100
4,195EdmondMillionColdTools4B32K
affine-6-5FvHJQbqn2sXCT21f2f5UaTGnrFXkPzA53HJ9ckmMjvk9Myj
jed351Cold4B32KVision
Gemma3-4B-ChatVector_SFT-from-IT_and_IT
EdmondMillionColdTools4B32K
affine-7-5EXDeevNLXBeWscrMYoCs9eNmfxiEd5tzSeR3DxkoDsZkiy7
EdmondMillionColdTools4B32K
affine-9-5CPgKCb7Whr16ADSPZh6RMkoQMk5jQyRA8vKpxvBH3hzynsC
surrey-nlpCold4B32KVision
ferrazzipietroCold4B32KVision
unsup-gemma-3-4b-it-datav3
JRQiCold4B32KVision
seed0_sample5000_mmmlu_google-gemma-3-4b-pt_en-ko_1.0-1.0_1.0
JRQiCold4B32KVision
seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-es_1.0-1.0_1.0
JRQiCold4B32KVision
seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-ko_1.0-1.0_1.0
UICHEOL-HWANGCold4B32KVision
glorious3jeremyColdTools4B32K
Johnny1024ColdTools4B32K
k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_material_sensitive20pct-pos_gap20pct
Johnny1024ColdTools4B32K
TTRL-sciknoweval_physics-TTRL-Len-8k-grpo-014723
kairawalCold4B32KVision
Gemma-3-4B-IT-HI-SynthDolly-1A-E8
kairawalCold4B32KVision
Gemma-3-4B-IT-TL-SynthDolly-1A-E5
kairawalCold4B32KVision
Gemma-3-4B-IT-ES-SynthDolly-1A-E8
kairawalCold4B32KVision
Gemma-3-4B-IT-TL-SynthDolly-1A-E8
kairawalCold4B32KVision
Gemma-3-4B-IT-ES-SynthDolly-1A-E1
kairawalCold4B32KVision
Gemma-3-4B-IT-PT-SynthDolly-1A-E1
kairawalCold4B32KVision
Gemma-3-4B-IT-TL-SynthDolly-1A-E1
JRQiCold4B32KVision
seed0_sample5000_bmlama_google-gemma-3-4b-it_en-zh_DPO_5e-06
EnergyAIColdTools4B32K
qwen3-4b-agrpo-think-lr3e-6
pettertonarCold4B32KVision
google-gemma-4b-relevance-v1
kairawalCold4B32KVision
Gemma-3-4B-IT-ES-SynthDolly-1A-E3
AnonymousNodeGAEColdTools4B32K
cold-start-alfworld-safety-sft-qwen-4b-1-global-step-171
Johnny1024ColdTools4B32K
TTRL-sciknoweval_chem-TTRL-Len-8k-grpo-132125
JRQiCold4B32KVision
seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_1.0-1.0_1.0
JRQiCold4B32KVision
seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_DPO_5e-06
JRQiCold4B32KVision
seed0_sample5000_bmlama_google-gemma-3-4b-it_en-zh_1.0-1.0_1.0
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_pos_sens_bottom20
EnergyAIColdTools4B32K
qwen3-4b-agrpo-think-lr5e-7
modrillColdTools4B32K
code_think_8_qwen3_4b_instruct_sft
kikansha-TomasuColdTools4B32K
Qwen3-4B-Instruct-2507-sft1