Re:Stability AI Launches the First of Its StableLM Suite of ...
by MacsHeadroom on Wednesday April 19, 2023 @09:38PM
(#35635368)
The base model is CC-BY-SA commercial licensed and you can finetune it in a couple of hours on a consumer GPU with 8GB of VRAM using https://github.com/johnsmith0031/alpaca_lora_4bit
Hopefully, people consider txtinstruct (https://github.com/neuml/txtinstruct) and other approaches to generate instruction-tuning datasets without the baggage.