Training large language models is a very technically demanding and resource intensive task. Many such models also require lots of specialized compute to use. Fortunately, we have recently been blessed by public releases of several "small" LLMs 1/4
LLMS
-
RAG Systems, LLMs, and LlamaIndex with Jerry Liu
By
–
Good morning fellow AI enthusiast! This week's iteration focuses on a new What's AI podcast episode with @jerryjliu0
, CEO and co-founder of @llama_index
! Explore RAG, LLMs, LlamaIndex, and more in this episode packed with insights for practitioners https://
open.substack.com/pub/louisbouch
ard/p/all-about-rag-systems-llms-and-multimodal?r=25qlky&utm_campaign=post&utm_medium=web&showWelcome=true
… -
Fine-tuning challenges and imperfect model performance issues
By
–
Not all of my fine-tunes work perfectly
-
Yi APIs Beta Program at Capacity with Exciting Updates Coming
By
–
Thank you for your incredible enthusiasm about Yi's APIs! Our beta program has reached capacity, but for the lucky ones with access, get ready for an exhilarating adventure! Don't forget to keep an eye out for more thrilling updates from Yi – there's plenty more to come!
-
Advocating for Machine-Generated Data in AI Learning
By
–
Humans largely learn from human-generated data. Machines currently learn from human-generated data. It makes sense for machines to learn from machine-generated data. x.com/peterjliu/stat…
-
Jerry Liu on AI Future: LlamaIndex, RAG, and LLM Solutions
By
–
@jerryjliu0 on the Future of AI: @llama_index, LLMs, RAG, Prompting and more!
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 19 décembre 2023
In this 25th episode, Jerry, co-founder and CEO of LlamaIndex shares valuable insights for anyone implementing LLM solutions. I decided to focus on Retrieval Augmented Generation (RAG) since it is the… pic.twitter.com/oIDkeSUsJ7@jerryjliu0 on the Future of AI: @llama_index
, LLMs, RAG, Prompting and more! In this 25th episode, Jerry, co-founder and CEO of LlamaIndex shares valuable insights for anyone implementing LLM solutions. I decided to focus on Retrieval Augmented Generation (RAG) since it is the -
Google Releases Seven LangChain Notebooks for Gemini Integration
By
–
LangChain x Google The official Google `generative-ai` repo has a ton of resources for getting started with Gemini This includes SEVEN different notebooks for using LangChain to orchestrate a Gemini-powered LLM app Dive into all the goodness: https://
github.com/GoogleCloudPla
tform/generative-ai/tree/main/language/orchestration/langchain
… -
Low-Resource Languages Enable GPT-4 Jailbreak Research
By
–
Exciting news from #NeurIPS2023! The "Low-Resource Languages Jailbreak GPT-4" paper by Zheng-Xin Yong, Cristina Menghini, and @stevebach from the Snorkel Research team has won the Best Paper Award in the Socially Responsible Language Modelling Research (SoLaR) 2023 Workshop!
-
Large Language Model Identity and Self-Awareness Questions
By
–
As a large language model, I don’t have the specifics on my true identity.
-
Language Learning Easier Than Intuitive Physics Prediction
By
–
It was quite obvious 5-10 years ago that learning the structure of language by predicting missing words was easier than learning, say, intuitive physics by predicting video.
We have had projects on both things at FAIR for almost 10 years, and the language side made progress much