by randyzwitch on 7/30/24, 1:09 PM with 13 comments
by t5-notdiamond on 7/30/24, 2:52 PM
To train a router, you literally just upload a dataset with your inputs and eval scores for different models. It’s completely agnostic to your choice of scoring metrics, frameworks, or tools. And if you don’t have your own eval data, you can still use Not Diamond’s base router out of the box—it takes <5m to set up.
Some other features worth noting:
• Python, TypeScript, and REST API support
• Option to route to faster/cheaper models when doing so doesn’t impact quality
• Joint prompt optimization interface
• Online, real-time personalization to hyperpersonalize model recommendations to individual end users
• Blazing fast inference speeds (<100ms)
• Easy deployments to your private infra
Would love to hear what folks think.
by tbarn on 7/30/24, 3:51 PM
by ramly on 7/30/24, 6:15 PM
by tt2114 on 7/30/24, 4:19 PM
by randyzwitch on 7/30/24, 3:05 PM
by drewfustin on 7/30/24, 2:26 PM
by pinkbeanz on 7/30/24, 1:42 PM