CODE

–

15 November 2023 23h29

That's a totally fair perspective. Just two thoughts, if I may be so bold: – Use the term "source available", not "open source"
– Consider an open source license in the future — MSFT Research's history is littered with projects that failed due to closed licenses!

→ View original post on X — @openai

OpenAI DevDay Breakout Sessions: New Developer Features

By

@openai

–

15 November 2023 23h00

Our OpenAI DevDay Breakout Sessions are now live on YouTube. Check out deeper dives of our new features for developers, techniques for maximizing LLM performance, and more.

→ View original post on X — @miketamir

Self-Attention Mechanism Implementation for Language Models

By

@miketamir

–

15 November 2023 21h02

Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch https://
bit.ly/3YL821l #AI #DeepLearning #MachineLearning #DataScience

Open License Apache 2 Unlocks Project Potential

By

–

15 November 2023 20h37

I'd *love* to see this great work reach its full potential — a fully open license such as Apache 2 would unlock that, I think.

Microsoft Confuses Open Source with Source Available

By

–

15 November 2023 20h28

IIRC in the past MSFT has confused "open source" with "source available" in their messaging. I guess that's what's happening here too.

Normalization Layers in Deep Learning Model Experiments

By

–

15 November 2023 19h36

Thanks for sharing this interesting work. What kind of normalisation layers did you model use for these experiments?

→ View original post on X — @langchain

RAG with SQL and Semantic Search using PGVector

By

@langchain

–

15 November 2023 19h20

RAG w/ SQL + Semantic Search with PGVector A new LangChain template from @manuelsoria_ focuses on doing RAG (retrieval augmented generation) via a combination of SQL and semantic search It does this by writing PostgresSQL – which with the PGVector plugin allows for