Congrats to @reedsmithllp partner Jack Nelson! As the article on LTN outlines, Jack was a key part of our growth and success ๐๐๐ https://t.co/4d7a9fCNVc
@Scobleizer@GroqInc From what I can tell, GPT4o is running 60-80 tokens per second. Groq is running ~300+ on Lama 3 70b. So thereโs still a massive spread in terms of speed
It's coming up soon. Get your tickets for Legal Innovators California!
Richard Tromans puts together this great #legaltech / GC conference in San Francisco!
AL talks to keynote speaker Zach Abramowitz about why he's excited for the Legal Innovators California conference, SF, June 4/5 ๐๐บ๐ธ๐คโ๏ธ๐
> Short 2.5 min intro - press play to watch ๐
#legaltech#lawtwitter#LegalInnovators#GenAI
๐ฆBuild your own RAG with Mistral-7B and LangChain
Using local models can enable chatbots over your data while ensuring your data never leaves your computer
Great for enterprise or privacy centric use cases
This blog post by Madhav Thaker is one of the best resources we've seen yet. Explains not only RAG (retrieval augmented generation) but also how to work with local models
Thanks to @Roger_M_Taylor for sharing!
Blog: https://t.co/otxRLmLwvi