[GitHub Trending] google-research/timesfm
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Google's time series foundation model; strong technical depth but only tangential to reader's core interests.
Google Research released TimesFM 2.5, a 200M parameter time-series foundation model (down from 500M) supporting up to 16k context length and 1k horizon quantile forecasts via an optional 30M head. The open-source PyPI package now includes Flax for faster inference, covariate support via XReg, LoRA fine-tuning with HuggingFace Transformers + PEFT, and an agent skill (SKILL.md) for programmatic orchestration. Integrated into BigQuery ML, Google Sheets, and Vertex Model Garden, it's available under `pip install timesfm[torch]` or `[flax]`.
google-research