gamescaling / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
95e9055 verified
|
Raw History Blame Contribute Delete
980 Bytes
metadata
title: GameScaling
emoji: 🎮
colorFrom: red
colorTo: green
sdk: gradio
sdk_version: 6.30.0
app_file: app.py
short_description: Game frame to next 200ms of keyboard & mouse actions
python_version: '3.12'
startup_duration_timeout: 1h
license: apache-2.0
models:
  - THUSI-Lab/GameScaling
  - THUSI-Lab/GameScaling-9B-S3
  - THUSI-Lab/GameScaling-2B-S3

Demo of GameScaling (Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds). Uses the authors' system-prompt template and action parser (gamescaling/, Apache-2.0).

Example image credits:

  • examples/doom_battle1.jpg: from THUSI-Lab/GameScaling (illustration frame shipped by the authors).
  • examples/minetest.jpg: "Minetest screenshot 2" by Kotolegokot, CC BY-SA 3.0, via Wikimedia Commons (resized).
  • examples/supertuxkart.jpg: "Supertuxkart-0.9-screenshot-2" by the SuperTuxKart dev team, CC BY 3.0, via Wikimedia Commons (resized).