Show HN: I built a tiny LLM to demystify how language models work

  • Thread starter armanified
  • Start date
  • Replies 0
  • Views 15
Status
Not open for further replies.
A

armanified

Guest
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food.
Fork it and swap the personality for your own character.


Comments URL: https://news.ycombinator.com/item?id=47655408

Points: 77

# Comments: 6
 
Status
Not open for further replies.
Top