Post by wh on X
How to train a 670B parameter model.
Let's talk about the DeepSeek v3 report + some comparisons with what Meta did with Llama 405B

4.5K likes36 repliesPosted Dec 26, 2024
ViralLoop
Your next post already worked.
Loading the post
Private to you, and used when you remix this post.
Analysis by ViralLoop — not written by the original author.
