Text Generation
Transformers
PyTorch
mpt
Composer
MosaicML
llm-foundry
custom_code
text-generation-inference

Finetuning MPT-7B-Storywriter in 4-bit

#26
by rmihaylov - opened

I just created this repo. Finetuning MPT-7B using consumer GPUs.

https://github.com/rmihaylov/mpttune

Very cool! I'd also encourage you to upstream anything you think is reasonable into the llm-foundry!

Sign up or log in to comment