README.md

metadata

license: apache-2.0
library_name: laya
base_model: convaiinnovations/laya
tags:
  - laya
  - system-one
  - android
  - phone-agent
  - decision-model

laya-android-control

Finetune of convaiinnovations/laya for Android phone control.

Training data

• Source: eros438/phone-decisions-ac.
• That file holds 18,354 decision rows.
• The rows convert xwm/AndroidControl.
• Training ran 4 epochs on a Kaggle T4 with laya-train defaults.

Results

Model	test operations accuracy
Base Laya-english	0.261
Head-only finetune	0.574
Full finetune	0.665

In-sample calibration gave accuracy 0.85 and ECE 0.037.

Use

import laya
agent = laya.load("arnabwithab/laya-android-control", device="cuda")
agent.predict("Goal: ...", {"operation": {"type": "choice",
    "instructions": "Which operation moves this phone task forward?",
    "criteria": {"TAP": "...", "TYPE": "...", "SCROLL": "...",
                 "BACK": "...", "WAIT": "...", "DONE": "..."}}})

Serve it with laya-serve pointed at this repo.