Feature Extraction
Transformers
Safetensors
English
multilingual
laya_browser
laya
custom_code
system-1
browser-agent
web-navigation
decision-model
mmbert
mind2web
tilelang
Instructions to use cklxx/laya-browser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cklxx/laya-browser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="cklxx/laya-browser", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cklxx/laya-browser", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download code/finetune/webgym/serve.sh from cklxx/laya-browser: direct link, hf CLI and curl.
- Browser
- Download file 567 Bytes
-
https://huggingface.co/cklxx/laya-browser/resolve/main/code/finetune/webgym/serve.sh
- Command line
-
hf download hf://cklxx/laya-browser/code/finetune/webgym/serve.sh
-
curl -L -o serve.sh https://huggingface.co/cklxx/laya-browser/resolve/main/code/finetune/webgym/serve.sh
567 Bytes
| # serve.sh start|stop|restart -- webgym server on :8811, tracked by pid file (never pkill by pattern) | |
| D=$(cd "$(dirname "$0")" && pwd); PIDF=${GYM_PIDFILE:-/tmp/webgym.pid}; LOG=${GYM_LOG:-/tmp/webgym.log} | |
| stop() { [ -f $PIDF ] && kill $(cat $PIDF) 2>/dev/null; rm -f $PIDF; sleep 0.5; } | |
| start() { nohup $D/../../.venv/bin/python $D/app.py 8811 > $LOG 2>&1 & echo $! > $PIDF; sleep 1.5; curl -s --noproxy '*' -o /dev/null -w "webgym %{http_code}\n" http://127.0.0.1:8811/t/flight/1; } | |
| case "$1" in start) start;; stop) stop;; restart) stop; start;; esac | |