DPO fine-tuned models Family, high performance
-
jpacifico/Chocolatine-3B-Instruct-DPO-Revised
Text Generation • Updated • 1.07k • 16 -
jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
Text Generation • Updated • 1.94k • 6 -
jpacifico/Chocolatine-3B-Instruct-DPO-Revised-Q4_K_M-GGUF
Text Generation • Updated • 65 • 5 -
jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
Text Generation • Updated • 74 • 1