niklub
niklub
Hello, team! Thanks for the excellent work. When working batch inference, sometimes encountering server-side error that completely interrupts the process: ``` new fill batch. #seq: 7. #cached_token: 1541. #new_token: 4....
It means that next steps are not encountered as valid train period
- check if requested model version is the same as loaded - warning or lazy load if not matched
API for removing everything related to the project