Freesolo (@freesoloco) header
Freesolo (@freesoloco) profile picture
San Francisco, CA, USA
Joined March 2025
We recommend Flash for narrow, high-volume tasks where you are currently paying a frontier model to do the same job on every request. Flash trains a LoRA adapter on an open-weight model to beat the frontier for that task.
1
282
Today we're excited to open source Flash: a post-training stack for open weight models Flash is designed to be cost-efficient and extendable. It handles training algorithms, compute provisioning, and model serving. Use Flash via the CLI or self host with your own hardware.
5
5
2
20
2,541
Not every AI interaction is best served with a large frontier model. There is a long tail of trillion-token use cases, from tagging to search, best served by a sub-10b-parameter model that runs in milliseconds and costs many orders of magnitude less than the frontier. We built Freesolo Flash to make training loops like SFT and RL easy and end-to-end completable through your coding agent.
77
38
10
215
29,615