All Posts
2023
Rough thoughts on Mixtral vs Open Source
December 13, 2023Knowing Enough About MoE to Explain Dropped Tokens in GPT-4
August 9, 2023Non-determinism in GPT-4 is caused by Sparse MoE
August 5, 2023Dumped Blog Ideas
July 2, 2023Why can TorToiSe be fine-tuned?
February 16, 2023Why can't TorToiSe be fine-tuned?
February 11, 2023The bleak future of Artificial Intelligence in Singapore
February 10, 2023Fast (5x) Inference with TorToiSe-TTS
February 5, 20232022
Contrastive Search might-not-be What You Need
December 12, 2022An Informal Reminder
December 2, 2022