TorchMultimodal is a @PyTorch library for training state-of-the-art multimodal multi-task models at scale. You can learn more and get started here https://
bit.ly/3XalYlA 6/6
OPEN SOURCE
-
TorchMultimodal: PyTorch Library for Multimodal Multi-Task Models
By
–
-
Open Atlas of 617M Predicted Metagenomic Protein Structures Released
By
–
We announced some of our latest work in protein folding earlier this month. You can explore the open atlas of 617M predicted metagenomic protein structures here ➡️ https://t.co/DX2ysKsuFf
— AI at Meta (@AIatMeta) 29 novembre 2022
5/6https://t.co/NFe6Qy7I8hWe announced some of our latest work in protein folding earlier this month. You can explore the open atlas of 617M predicted metagenomic protein structures here https://
esmatlas.com 5/6 -
Easy Feature Addition Discussed for LangChain Repository
By
–
hah @sjwhitmore and i were discussing that! we ended up not implementing yet but should be an easy addition… made a ticket! https://
github.com/hwchase17/lang
chain/issues/224
… if you want to tackle could be a good first pr… otherwise i think we can probably get it in in the next few days! -
LangChain 0.0.24: Logging Improvements and Advanced AI Models
By
–
LangChain version 0.0.24 Add chain name for better logging (@Hansenq)
Bump default @OpenAI model to `text-davinci-003` (!!!) (@shyamalanadkat)
PaL (Program-aided Language Models) Chain (!!!) with help from @aman_madaan et co. https://github.com/hwchase17/langchain
… -
Predibase CEO presents low-code ML systems at TMLS2022
By
–
Hope to see everyone at #TMLS2022 today! Piero Molino, Predibase CEO & creator of open-source http://
Ludwig.ai is leading a talk on how #lowcode declarative ML systems enable teams to rapidly build, iterate and deploy state-of-the-art models. https://
pbase.ai/TMLS22 -
Data Science Skills: Staying Competitive in AI Era
By
–
Infographic: Data Science – staying ahead. #BigData #Analytics #DataScience #AI #MachineLearning #IoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #React #Serverless #DataScientist #Programming #Coding #100DaysofCode #DevOps #GitHub #SQL
-
Datasette lacks collaborative online service and reporting features
By
–
Datasette is great (thanks @simonw
!) but there isn't really a collaborative online service for it AFAIK, and forms and reports would require a bunch extra. -
LangChain Default OpenAI Model Updated to text-davinci-003
By
–
@shyamalanadkat already submitted a PR to change the default OpenAI model to `text-davinci-003` in LangChain https://
github.com/hwchase17/lang
chain/pull/215
… That was fast! -
Create Custom Memory Modules for LangChain Chains
By
–
And here's how you can create your own custom memory module! https://
langchain.readthedocs.io/en/latest/exam
ples/memory/custom_memory.html
… This can be used to implement your own ideal memory structure and then easily plug it into any chain. -
Expanding Memory Types in LangChain With Community Contributions
By
–
There are many more types of memory we hope to add! @sjwhitmore has been pioneering this effort so far, and we hope a lot of these come from the community. Check out this idea from @BrennanErbz for inspiration