GamerUntouch's picture
Update README.md
f006fc5
metadata
license: apache-2.0

A collection of LoRAs for int8 LLaMA trained on an assortment of literature (approximately 16 MB) for 2 epochs.

UPDATE: 2024-04-18 Retrained using Transformers 4.28.1, on two epochs, with a small amount more data.

Notes for usage.

- These models are not instruct LoRAs. They are designed to supplement existing story data.
- There will likely be some bleedthrough on locations and names, this is especially notable if you use with very little context.
- There isn't any large notable formatting, ### seperated stories in the dataset, and *** seperated chapters.