Train OpenChat on Mistral-10.7B-v0.2

#12
by Joseph717171 - opened

OpenChat team, I Depth Up-Scaled Mistral-7B-v0.2, following UpStage’s paper: SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling, if you are interested in training OpenChat on a slightly bigger model.

Joseph717171/Mistral-10.7B-v0.2

  • 32K Context Window
  • 🚫 Sliding Window Attention

Sign up or log in to comment