DPO fine-tuned models Family, high performance
-
jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
Text Generation • Updated • 8.37k • 15 -
jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
Text Generation • Updated • 2.76k • 9 -
jpacifico/Chocolatine-3B-Instruct-DPO-Revised
Text Generation • Updated • 148 • 26 -
jpacifico/Chocolatine-Admin-3B-SFT-v0.3b
Text Generation • Updated • 66 • 4