Many of the mobile experiences people know and love across our apps like Facebook & Instagram are made possible by running AI models on-device. Today, we’re sharing more information about how Meta uses @PyTorch to enable these experiences
CODE
-
LangChain 0.0.27 Release with ReActTextWorldAgent
By
–
LangChain version 0.0.27: Much appreciated clean up and formatting by `tonyabracadabra` (if you are on Twitter, lmk!!) ReActTextWorldAgent: a new agent from @JavaFXpert – see below for more!
-
LLM Meme Generator and Semantic Search Research Projects
By
–
[2/2] @gunaratne_rahel : Research Paper Semantic Search/Clustering @SalluMandya : Viral Meme Generator using Large Language Models Sign up now and let’s celebrate the holiday season together https://
short.cohere.ai/colabfridayhol
iday
… -
BigCodeProject Party and The Stack Release Success
By
–
The @BigCodeProject party was a triple success: great project, exciting new release of The Stack and…. I finally got to meet @DynamicWebPaige in real life
-
Transformers and Accelerate Support Latest PyTorch Nightlies
By
–
This is already supported in the latest releases of Transformers and Accelerate, so you can try it today if you install PyTorch from the nightlies!
-
PyTorch 2.0 Compiler Delivers Major Training Speedups
By
–
Today the PyTorch team announced a 2.0 milestone, with focus on a new compiler speeding up PyTorch models with zero change in code. We tried it out in the past few weeks and here are the speedups we observed in our canonical training examples.
-
Streamlit: Fast Data App Development Without Frontend Knowledge
By
–
.
@streamlit is one of the most useful and fastest way to build quick data apps without knowing any front-end technologies. If you are looking to learn how to build streamlit apps with code examples then check out the below repo is a must checkout -
MLflow 2.0 Simplifies Data Science Workloads and MLOps
By
–
#MLflow 2.0 has entered the chat By simplifying #data science workloads and delivering innovative, first-class tools for #MLOps, MLflow is now better than ever. See the latest updates https://
dbricks.co/3tAv3qy -
MLOps: Implementing Procedures and Best Practices for AI Production
By
–
Adopting MLOps means putting in place procedures and best practices to maintain models for executing artificial intelligence inferences in production formally and efficiently. The name mimics the DevOps nomenclature model. Microblog and social design by @antgrasso #MLOps #AI
-
Catherine Adenle Daily: AI and Coding News Digest
By
–
The latest The Catherine Adenle Daily! https://
paper.li/CatherineAdenl
e?edition_id=c26fcaf0-7206-11ed-9d70-fa163ed80008
… Thanks to @JeroenBartelse @RosyCoaching #100daysofcode #bot