Hi everybody!

Inspired by a recent thread, mentioning the insane goliath abilities I decided to merge four SFT Yi models to make 2 seperate 55B Yi, one with context 200K and one with 32K.

Try them out and let me know!

  • BalorNGB
    link
    fedilink
    English
    arrow-up
    1
    ·
    11 months ago

    Did you do post-merge retraining? Without at least some results are going to be poor…