Instructions to use mlboydaisuke/Timestral-209M-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use mlboydaisuke/Timestral-209M-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
11 days ago
-
Demo re-taken with the sample's chart fixed (the forecast starts at the last observed value): graph call 18.0 ms, host 7.1 ms, first NPU compile 23.6 s in that run
Verified signatureac11baa
13 days ago
-
Demo: a new clip with a year of daily orders (365 values) pasted in, so the forecast sees the series' 13-week cycle; card Demo text updated
Verified signature9d6e08a -
Card: a first sentence with the converter, the phone and two speeds; a Demo section with the Android sample's clip (assets/demo.mp4, assets/demo.gif)
Verified signatureff9034d -
Timestral-209M on LiteRT: float16 graphs for the GPU and the NPU, int8 graphs for the CPU, host code in Python and Kotlin
Verified signature11f5cc3