Show HN: Python SDK – forecasting with foundation time-series and tabular models g github.com 43 ChernovAndrei 10 months ago 18 comments
Show HN: UI front end to forecast with foundation time-series models f faim.it.com 1 ChernovAndrei 11 months ago 0 comments
Show HN: MCP Server for Time-Series Forecasting g github.com 1 ChernovAndrei 11 months ago 1 comments
Show HN: JavaScript SDK for zero-shot time-series forecasting (Chronos2, TiRex) g github.com 2 ChernovAndrei 11 months ago 0 comments
Show HN: Serverless platform for inference of time-series foundation models f faim.it.com 1 ChernovAndrei 1 year ago 0 comments
For Chronos-2 (the current state of the art in time-series modeling), the setup is almost identical to that of LLMs because it is based on the T5 architecture. The main difference is that, in time-series models, tokens correspond to subintervals in the real-valued (ℝ) space. You can check the details here: https://arxiv.org/pdf/2510.15821