tech
2023
Knowing Enough About MoE to Explain Dropped Tokens in GPT-4
August 9, 2023Non-determinism in GPT-4 is caused by Sparse MoE
August 5, 2023Why can TorToiSe be fine-tuned?
February 16, 2023Why can't TorToiSe be fine-tuned?
February 11, 2023Fast (5x) Inference with TorToiSe-TTS
February 5, 20232022
Contrastive Search might-not-be What You Need
December 12, 2022Why Language Models?
November 27, 2022Recent ML Projects
November 27, 2022Multiprocessing and random()
October 2, 2022Disco Narrator - Data Formatting
September 25, 2022