Skip to content
View shabani1's full-sized avatar

Block or report shabani1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shabani1/README.md

Hello world 👋

I'm currently working on Lexy AI. Previously, I founded and led the AI team @ Replit.

Before Replit, I was a quant building investment strategies using Machine Learning and NLP on massive unstructured datasets.

Some links to my work:

  • 💻 My blog post on How to train your own Large Language Models.
  • 🎙️ My interview on the Latent Space podcast with Swyx & Alessio.
  • 📰 Hacker News post and discussion on training replit-code-v1-3b.
  • 📽️ My presentation at Databricks' Data+AI Summit on How to train your own LLMs (slides).
  • 🥾 My session at The Full Stack's LLM Bootcamp on LLM training (slides).
  • 🧠 Joint presentation at Google Brain on Emerging Research & Applications of LLMs.

📫 Reach out to me on LinkedIn.

Pinned Loading

  1. lexy-ai/lexy lexy-ai/lexy Public

    Data pipelines for AI applications

    Python 10