[ML News] Google’s 540B PaLM Language Model & OpenAI’s DALL-E 2 Text-to-Image Revolution
#mlnews #palm #dalle2
Google releases PaLM and OpenAI releases DALL-E 2 (and more news).
Sponsor: Weights & BIases
Start here: https://wandb.me/yannic
Thumbnail credit: DALL-E 2 via Sam Altman
OUTLINE
0:00 – Street interview w/ random stranger
2:45 – Intro
3:10 – PaLM – Google’s 540B Pathways Language Model
8:10 – Sponsor: Weights & Biases
9:30 – OpenAI releases DALL-E 2
12:25 – Open Source Datasets and Models
13:40 – Salesforce releases CodeGen
My Live Reaction to DALL-E 2: https://youtu.be/gGPv_SYVDC8
My Video on GLIDE: https://youtu.be/gwI6g1pBD84
My Video on the Pathways System: https://youtu.be/vGFaiLeoLWw
References:
PaLM – Google’s 540B Pathways Language Model
https://ai.googleblog.com/2022/04/pathways-language-model-palm-scaling-to.html
https://storage.googleapis.com/pathways-language-model/PaLM-paper.pdf
OpenAI releases DALL-E 2
https://openai.com/dall-e-2/
https://cdn.openai.com/papers/dall-e-2.pdf
https://www.instagram.com/openaidalle/
Have an idea for DALL·E? Reply with a caption. I'll generate 20 or so!
— Sam Altman (@sama) April 6, 2022
https://twitter.com/sama/media
Today we released #dalle 2 – a model which can generate incredibly impressive images based on a textual description!
"A cobra, surfing on a big wave"
(Feel free to drop suggestions in the thread – I'll generate and share if they are fun!) pic.twitter.com/lKRtEESzAs
— Boris Power (@BorisMPower) April 6, 2022
I've always wanted to be a cool panda riding a skateboard in Santa Monica. Generated with DALL-E 2 🙂#dalle pic.twitter.com/IIdKF83Tlc
— Aris Konstantinidis (@ariskonstant) April 6, 2022
Open Source Datasets and Models
Very exciting 'breaking' news!
CompVis (research group behind VQGAN) have just released a new 1.45B parameter model to its Latent Diffusion model: https://t.co/hToojGe6wI
From the released image it seems like it has an unprecedented text-synthesis capacity. More to follow soon pic.twitter.com/om3n4gsReQ
— multimodal ai art (@multimodalart) April 4, 2022
LAION-5B: A new era of open large-scale multi-modal datasets
https://github.com/mlfoundations/open_clip
Salesforce releases CodeGen
https://github.com/salesforce/CodeGen
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191
If you want to support me, the best thing to do is to share out the content 🙂
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n