time seriesfamily
Temporal Fusion Transformer (TFT)
Attention-based model for interpretable multi-horizon forecasting with static, known and observed inputs. Paper by Lim et al. (2019).
Levelfamily
Classtime series
Parametersnot in the notes
Contextnot in the notes
Released19 Dec 2019
Opennessopen source
Runs onnot in the notes
Statusactive
Lineage
Intel time-series-forecasting-electricity-0001 belongs to this familytime seriesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
Identity
- Developer
- University of Oxford, Google
- Family
- not in the notes
- Released
- 19 Dec 2019 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- hybrid Recurrent layers for local processing plus interpretable self-attention
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- time series
- Output
- time series
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- Apache License 2.0 sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Licence is that of the Nixtla neuralforecast implementation (Apache-2.0). NVIDIA Deep Learning Examples publishes trained checkpoints (electricity, traffic) on NGC.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelTemporal Fusion Transformer (TFT)University of Oxford, time series
Temporal Fusion Transformer (TFT)University of Oxford, time seriesUse CasesIndustrial Forecasting (Load, Throughput, Demand)IndustrialDemand ForecastingRetail and LogisticsUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Sources
- arxiv.org/abs/1912.09363 https://arxiv.org/abs/1912.09363
- github.com/Nixtla/neuralforecast https://github.com/Nixtla/neuralforecast
- nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html
- catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/tft_base_pyt_ckp... https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/tft_base_pyt_ckpt_ds-electricity
- arxiv.org/html/1912.09363 https://arxiv.org/html/1912.09363
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Temporal Fusion Transformer (TFT)", https://aurion.semai.id/models/temporal-fusion-transformer/, records of October 2026.