AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Multimodal, Multi-Lingual NLP at Hugging Face with John Bohannon and Douwe Kiela - #589
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Tokenization of the Language Model
The main architecture is exactly what you would expect. There are some nifty new things in there so it uses like LMI for like how to do the token embeddings and things like that. It's a basic text to text autoregressive model same architecture as your typical big text to text models yeah basically. I think this is a really neat part of NLP just very much I like the tools you use kind of talk but let's just like take a moment tell us what is a tokenWhat is a tokenizer and then like how did you do it differently with this big Bloom model?
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode