Text Classification
Transformers
Safetensors
Laya
English
system-one
decision-model
android
mobile-agent
gui-agent
accessibility
androidcontrol
mmbert
Eval Results (legacy)
Instructions to use ByunByun/laya-android with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ByunByun/laya-android with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ByunByun/laya-android")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ByunByun/laya-android", device_map="auto") - Laya
How to use ByunByun/laya-android 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 laya_android_metadata.json from ByunByun/laya-android: direct link, hf CLI and curl.
- Browser
- Download file 763 Bytes
-
https://huggingface.co/ByunByun/laya-android/resolve/main/laya_android_metadata.json
- Command line
-
hf download hf://ByunByun/laya-android/laya_android_metadata.json
-
curl -L -o laya_android_metadata.json https://huggingface.co/ByunByun/laya-android/resolve/main/laya_android_metadata.json
763 Bytes
| { | |
| "base_model": { | |
| "repo": "convaiinnovations/laya", | |
| "subfolder": "multilingual", | |
| "revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", | |
| "laya_package": "0.3.28" | |
| }, | |
| "max_len": 3072, | |
| "head_max_len": 1536, | |
| "training": { | |
| "laya_android": { | |
| "name": "laya-android-v0", | |
| "base": "multilingual", | |
| "train_steps": null, | |
| "seed": 0, | |
| "epochs": 3, | |
| "micro_batch": 8, | |
| "grad_accum": 4, | |
| "encoder_lr": 2.5e-05, | |
| "head_lr": 0.0001, | |
| "loss": "soft-ce", | |
| "shuffle_options": [ | |
| "choice" | |
| ], | |
| "gradient_checkpointing": true | |
| }, | |
| "best_epoch": 2, | |
| "train_hours": 2.726, | |
| "hardware": "NVIDIA GeForce RTX 4090" | |
| }, | |
| "evaluations": [ | |
| "final_metrics.json", | |
| "base_metrics.json", | |
| "rtx4090.json" | |
| ] | |
| } |