metadata
library_name: granite_tsfm
base_model: ibm-granite/granite-timeseries-ttm-r2
tags:
- ttm4hvac
- tsfm
- digital twin
- hvac
- energy
- experiment
license: apache-2.0
datasets:
- gft/ttm4hvac-target-default-train
- gft/ttm4hvac-target-heat-test
- gft/ttm4hvac-target-cool-test
pipeline_tag: time-series-forecasting
papers:
- title: >-
Transfer learning of building dynamics digital twin for HVAC control with
Time-series Foundation Model
url: https://arxiv.org/abs/XXXX.XXXXX
authors: Ferran Aran Domingo
TTM4HVAC – TinyTimeMixer for HVAC dynamics modeling
This repository contains the TTM4HVAC – target-default fine-tuned TinyTimeMixer model.
It corresponds to the “target-default” experiment from the TTM4HVAC paper, where the model is fine-tuned solely on default RBC data from the target building (BestestAir, Denver climate).
This checkpoint is part of the TTM4HVAC experiment family.
For the main model, recommended usage, detailed examples, and full documentation, please see:
👉 Main model card: https://huggingface.co/gft/ttm4hvac