how "merged" is this one?
#3
by
sirus
- opened
I've seen some pretty crazy lora merges. Just wondering the details of this model. It's currently number 2 on the open llm leaderboard, but the model card is blank.
So mysterious
also this appears not to be ggml
It's just part of qlora research, you can lookup in other timdettmers models. Usually no one starts from 65B model, and it's pretty tedious to explain the same thing in dozens of similar model cards. Most people here are already familiar with how to use it, if you are not - check the qlora github repository mantioned above, there is a lot of good explanations there.
Yes it's not ggml - it uses the standard huggingface transformer library. Check out this colab for inference example.