You May Also Enjoy
Using github and hugging face to manage projects
3 minute read
Published:
I often switch between multiple machines/rented servers for DL projects, so here is a quick personal note: how I use GitHub CLI (gh) to manage code and Hugging Face to manage models and datasets. Below is my usual command list and quick setup notes.
DeepSeek pretrain data
8 minute read
Published:
This series of blogs will introduce the techniques used in DeepSeek Team’s papers.
Deepseek pretrain dataset
5 minute read
Published:
1. Proximal Policy Optimization (PPO)
DeepSeek Architecture
4 minute read
Published: