Instructions to use FluidInference/laya-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use FluidInference/laya-coreml with Laya:
# 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
|
Download NOTICE.md from FluidInference/laya-coreml: direct link, hf CLI and curl.
- Browser
- Download file 1 kB
-
https://huggingface.co/FluidInference/laya-coreml/resolve/main/NOTICE.md
- Command line
-
hf download hf://FluidInference/laya-coreml/NOTICE.md
-
curl -L -o NOTICE.md https://huggingface.co/FluidInference/laya-coreml/resolve/main/NOTICE.md
1 kB
Notices
This repository
Core ML conversion of the laya-multilingual decision model, by Fluid Inference.
Licensed under the Apache License, Version 2.0; see LICENSE.
Upstream model and code
The converted weights and the reference implementation are the work of Convai Innovations and contributors, used under the Apache License, Version 2.0.
- Weights:
convaiinnovations/laya, subfoldermultilingual, revision1c5edc17a7acd8701df6fc341c0d179f1c62c982. - Reference implementation:
NandhaKishorM/laya.
The encoder is jhu-clsp/mmBERT-base,
and tokenizer.json carries its vocabulary, redistributed under that model's terms.
No weights were retrained. The conversion changes tensor precision and fixes input shapes; the parameters are the upstream ones. This is an independent conversion and is not an official Convai Innovations release.