Show HN: DeepSeek V3 in ~200 lines of pure Jax
A project demonstrating the DeepSeek V3 model using approximately 200 lines of pure Jax code.
Hacker News submitter: VaibhaavTiwari
Submitted to Hacker News:
A project demonstrating the DeepSeek V3 model using approximately 200 lines of pure Jax code.
Hacker News submitter: VaibhaavTiwari
Submitted to Hacker News: