Sanyam Bhutani
@bhutanisanyam1
๐จโ๐ป Sr Data Scientist @h2oai | Previously: @weights_biases ๐ Podcast Host @ctdsshow ๐จโ๐ International Fellow @fastdotai ๐ฒ Grandmaster @Kaggle
ID:784597005825871876
https://www.youtube.com/c/chaitimedatascience 08-10-2016 03:31:18
7,9K Tweets
34,5K Followers
994 Following
Congrats to AI at Meta on Llama 3 release!! ๐
ai.meta.com/blog/meta-llamโฆ
Notes:
Releasing 8B and 70B (both base and finetuned) models, strong-performing in their model class (but we'll see when the rankings come in @ lmsys.org :))
400B is still training, but already encroachingโฆ
RAG vs. Fine-Tuning debates drive me nuts. They are not fungible replacements for each other. Dan Becker and I are teaching a free lighting course on the topic
maven.com/p/787a2f/rag-aโฆ
A few weeks ago, I had an incredible conversation with Jeremy Howard
We chatted all things AnswerAI (his new startup), FastAI, and more. I hope you enjoy this as much as I did ๐ซถ
youtu.be/OujUZnXf4J0?siโฆ
There are a growing number of voices expressing disillusionment with fine-tuning.
I'm curious about the sentiment more generally. (I am withholding sharing my opinion rn).
Tweets below are from Emmanuel Ameisen anton Ethan Mollick
The incredible Radek Osmulski ๐บ๐ฆ was kind enough to interview me ๐
We talked about:
- My journey into programming
- How fastai changed my life
- Why I started my podcast series
- My approach to goal setting
- Reading LLM papers
Thanks again Radek!
m.youtube.com/watch?v=JrwO7fโฆ
You need to put 2x the quantity as your goal, where x is the quantity you can achieve easily in a week.
Eg: you should aim daily 2 hours to read paper, if you can comfortably read 1 hour now.
- Sanyam Bhutani said this during an interview with Radek.
youtu.be/JrwO7f2C__U?siโฆ
After watching the video
youtu.be/haRCu4hoI2A?siโฆ
I have started reading this book.
I will be posting some ideas from this book.
Thanks Sanyam Bhutani and Radek Osmulski ๐บ๐ฆ
Last week, Radek Osmulski ๐บ๐ฆ and I got to hangout with the CEO of Answer.ai ๐
Jeremy Howard has always been very kind to us with his time
Also, he owns a large beach in Brisbane so that makes it an awesome trip ๐
A perfect intro to open source LLMs! ๐
The course by Amit Sangani is now my top recommendation for getting started with Large Language Models:
- Just enough theory for a whole picture
- Teaches prompting, special tokens and conversational agents
- Perfectly abstracts theโฆ
After 3 years of learning, being mentored and building with this legend
I finally met Aman Arora in person! ๐