I expanded this tweet into...an essay
rosanneliu.com/post/i-hope-yo…

I’m excited to share that I’ve joined Answer.AI as member of the technical staff for R&D!

I’m really excited to join such a small yet highly creative and productive team—led by Jeremy Howard and Eric Ries—in pursuit of practical, development-driven LLM breakthroughs!

Today at Answer.AI we've got something new for you: FSDP/QDoRA. We've tested it with AI at Meta Llama3 and the results blow away anything we've seen before.

I believe that this combination is likely to create better task-specific models than anything else at any cost. 🧵

Vik is an extraordinary person. He won the challenging Kaggle essay scoring competition, founded the super successful company Dataquest, created top tier NLP tools like Surya & Marker, & more.

Now he's joining Answer.AI.

Read his journey to deep learning mastery here:

We've just published diffusion course by Jonathan Whitaker Lewis Tunstall et al. at hf.co/learn/diffusio…

It is a great resource to learn the basics of diffusion models & diffusers

Document reranking is powerful, but daunting to get started with.

Moreover, trying a new approach requires modifying your pipeline, even though it does the same thing!

Introducing 🔧rerankers: a lightweight library to provide a unified way to use various reranking methods🧵1/?

This is very exciting! Neural Magic has the best CPU kernels for LLM inference and now they are expanding to GPUs. Curious about their performance!

Thanks to the amazing work of Jeremy Howard, the Answer.AI team (special thanks to Jonathan Whitaker & Benjamin Warner for walking through the changes with me) for getting FSDP + QLoRA working.

We've managed to integrate their findings into Axolotl and now have additional