asedmammad/
lhk-dpo

23 1 year ago

DPO finetuned model from FusionNet_7Bx2_MoE_14B

Models

View all →

1 model

lhk-dpo:v1-q5_K_M

9.1GB · 32K context window · Text · 1 year ago

Readme

LHK_DPO_v1 is trained via Direct Preference Optimization(DPO) from https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_14B.

Original model is from https://huggingface.co/HanNayeoniee/LHK_DPO_v1