Open Source Musings & Snow Time

Welcome! Here’s where I write thoughts on various open source Large Language Model projects and random things I’m doing. I’m a former Staff Software Engineer from Google Translate and until I make it back the states, I’m spending some time exploring the world of smaller teams and companies. I sometimes take on contractor work related to LLMs. During winter, I spend a lot of time skiing in Hakuba Japan (if you find yourself there, say hello and I can show you around).

Recent Posts

Upcoming Reviews

• Making KT-Villa with FastChat, LLaVa & RedwoodJS:
  • A basic overview
  • Gluing Stable Diffusion and Llava together
  • Piping in Zephyr-7b
  • Why the rest of the project was still hard
• Evaluate some interesting projects:
  • ModelFusion
  • llama-cpp-python
  • xorbitsai/inference
  • Lilac
• Try out some more models:
  • teknium/OpenHermes-2.5-Mistral-7B
  • teknium/Mistral-Trismegistus-7B
  • liuhaotian/llava-v1.5-7b

Selected Publications

Guo, Mandy, Yinfei Yang, Keith Stevens, Daniel Cer, Heming Ge, Yun-hsuan Sung, Brian Strope, and Ray Kurzweil. 2019. “Hierarchical Document Encoder for Parallel Corpus Mining.” In Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers). Florence, Italy: Association for Computational Linguistics. https://aclanthology.org/W19-5207.

Jurgens, David, and Keith Stevens. 2010. “The s-Space Package: An Open Source Package for Word Space Models.” In Proceedings of the ACL 2010 System Demonstrations. Uppsala, Sweden: Association for Computational Linguistics. https://aclanthology.org/P10-4006.

Köpf, Andreas, Yannic Kilcher, Dimitri von Rütte, Sotiris Anagnostidis, Zhi-Rui Tam, Keith Stevens, Abdullah Barhoum, et al. 2023. “OpenAssistant Conversations – Democratizing Large Language Model Alignment.” https://arxiv.org/abs/2304.07327.

Wu, Yonghui, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, et al. 2016. “Google’s Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation.” CoRR abs/1609.08144. http://arxiv.org/abs/1609.08144.