Hey, Iām Baptiste Colle, a Machine Learning Engineer at Hugging Face š¤. I work on the optimization team, where my focus is on ensuring that large language models (LLMs) perform efficiently and effectively in real-world applications.
At Hugging Face, I tackle the exciting challenge of making LLMs go “brrr” ā fast and powerful. My work involves:
- Optimizing model inference for speed and efficiency
- Reducing computational requirements while maintaining performance
- Implementing cutting-edge techniques to improve model throughput
Get in Touch
Interested in discussing machine learning optimization, LLMs, or potential collaborations? Feel free to reach out through any of the channels below:
- Email: [email protected]
- LinkedIn: linkedin.com/in/baptistecolle
- GitHub: github.com/baptistecolle