aloobun's picture
Update README.md
b036c6f
metadata
license: apache-2.0
datasets:
  - totally-not-an-llm/EverythingLM-data-V3
language:
  - en
tags:
  - openllama
  - 3b

Trained on 3 epoch of the EverythingLM data.

Eval Results :

image/png

I like to tweak smaller models than 3B and mix loras, but now I'm trying my hand at finetuning a 3B model. Lets see how it goes.