Domi Yan
8 posts
I’m pleased to announce Gecko 🦎, a new text embedding model developed at @GoogleDeepMind and now available on @googlecloud ! Gecko is powered by an LLM distillation recipe, and is one step towards our goal to bridge LLM and retrievers. Promptagator 🐊, Gecko🦎, what’s next?
Jinhyuk Lee@leejnhk
Introducing Gecko 🦎, a new text embedding model from Google DeepMind! Distilled from LLMs, Gecko offers powerful embeddings for various NLP tasks. Gecko is now available in Google Cloud API 👉bit.ly/google-gecko-a… Paper: bit.ly/google-gecko Colab: bit.ly/google-gecko-c…
English
Domi Yan retweetledi
Cerebras Systems sets record for largest AI models ever trained on one computer. venturebeat.com/2022/06/22/cer…
English
@ZhuyunDai Interesting work. Reading technical documents/Wikipedia can be boring and frustrating. This invention could provide a path to make it interactive and more fun!
English
Checkout our new paper! Dialog Inpainting: Turning Documents into Dialogs
Kelvin Guu@kelvin_guu
Automagically✨ turn any document into a dialog using Dialog Inpainting🎨: arxiv.org/abs/2205.09073 Today's chatbot training datasets cover a tiny fraction of topics/domains. To fix this, we turn 19M web pages into dialogs, delivering SotA across 3 conversational QA benchmarks!
English
Domi Yan retweetledi
We wrote our @PyTorch implementation to take full advantage of our WSE’s 850,000 #AI-optimized cores, explains our Senior Director @EmadBarsoumPi. Read his blog to learn more: hubs.li/Q01831Nt0 #pytorch #deeplearning
English
