Instructions to use kloodia/laya-executorch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use kloodia/laya-executorch 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 meta.json from kloodia/laya-executorch: direct link, hf CLI and curl.
- Browser
- Download file 672 Bytes
-
https://huggingface.co/kloodia/laya-executorch/resolve/main/meta.json
- Command line
-
hf download hf://kloodia/laya-executorch/meta.json
-
curl -L -o meta.json https://huggingface.co/kloodia/laya-executorch/resolve/main/meta.json
672 Bytes
| { | |
| "source": "convaiinnovations/laya/multilingual", | |
| "role": "localia-command-gate", | |
| "modalities": [ | |
| "text" | |
| ], | |
| "languages": "100+", | |
| "quant": { | |
| "ios": "mlx weight-only int4 group32 + embedding int8", | |
| "android": "xnnpack 8da4w (int8 dynamic act + int4 weights group32)" | |
| }, | |
| "max_len": 2048, | |
| "max_opts": 4, | |
| "android": "android/laya_gate_xnnpack_8da4w.pte", | |
| "ios": "ios/laya_gate_mlx_int4.pte", | |
| "inputs": [ | |
| "input_ids[1,2048] long", | |
| "attention_mask[1,2048] long", | |
| "marker_pos[1,4] long", | |
| "marker_mask[1,4] bool", | |
| "qtype[1] long (0=choice, 1=score, 2=noul)" | |
| ], | |
| "output": "logits[1,4] float", | |
| "license": "Apache-2.0" | |
| } | |