Simple Thoughts
All Posts Tags Categories About
Simple Thoughts
Cancel
All PostsTagsCategoriesAbout

 tech

2024

Calculating the Cost of a Google Deepmind Paper July 30, 2024
DeepSeek Core Readings 0 - Coder June 30, 2024
DeepSeek Core Readings 1 - LLM June 23, 2024

2023

Rough thoughts on Mixtral vs Open Source December 13, 2023
Knowing Enough About MoE to Explain Dropped Tokens in GPT-4 August 9, 2023
Non-determinism in GPT-4 is caused by Sparse MoE August 5, 2023
Why can TorToiSe be fine-tuned? February 16, 2023
Why can't TorToiSe be fine-tuned? February 11, 2023
Fast (5x) Inference with TorToiSe-TTS February 5, 2023

2022

Contrastive Search might-not-be What You Need December 12, 2022
  • 1
  • 2
2022 - 2025 152334H