Hugging Face Blog·· 29 d ago
Training a coding model to paint watercolours with TRL and OpenEnv
Training a coding model to paint watercolours with TRL and OpenEnv
AI summary
A Hugging Face blogger reproduced Surya Narreddi's idea of having a language model paint watercolours using TRL and OpenEnv. The model paints through around 150 lines of JavaScript with p5.brush, with datasets, RL environments, training scripts and models all open-source.
Selection record
Threshold 60Official, first-handFirst 58Second 42
Not admittedSum of both 100 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：训练编码模型用RL绘制水彩画，含TRL/OpenEnv技术细节
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co