Not sure I get it. The model you're improving is local? If so how do you even calculate cost compared to an API
Open source models.
wmo routes requests between frontier models and open source models that continuously train using Tinker. As the smaller models improve, more traffic gets routed to them.
Calculating cost is just tokens in/out.
alt Hacker News
Open source models.
wmo routes requests between frontier models and open source models that continuously train using Tinker. As the smaller models improve, more traffic gets routed to them.
Calculating cost is just tokens in/out.