Amu's picture
init model
d61b184
metadata
license: apache-2.0
datasets:
  - HuggingFaceFW/fineweb-edu
language:
  - en

It's a super tiny llama3 model.

It has 0.247B parameters.

It is pretrained on the fineweb-edu dataset.(10B)

I hope I can make it beter and better.

If you see it, please give me a like. Thanks.

More info will be added later.