Zephyr: Direct Distillation of LM Alignment Tunstall et al.: https://
arxiv.org/abs/2310.16944 #ArtificialIntelligence #DeepLearning #MachineLearning
LLMS
-
Zephyr: Direct Distillation of LM Alignment
By
–
-
Psychologists Study LLM Capabilities and Cultural Impact
By
–
Awesome study led by @AlisonGopnik on the capabilities of LLMs from the psychologists' standpoint. Quote: "Large language models such as ChatGPT are valuable cultural technologies. They can imitate millions of human writers, summarize long texts, translate between languages,
-
Transformer Architecture: Foundation of Generative AI
By
–
Generative AI exists because of the transformer https://
bit.ly/3FxyCn6 #AI #MachineLearning #DeepLearning #LLMs #DataScience -
3D-LLM: Bridging Language and 3D World Perception
By
–
With these evolutions come new tools and models such as the 3D-LLM. This novel model is bridging the gap between language and the 3D world around us. It shows potential not just to perceive the world but also act within it.
-
LangChain RAG Overview: Basics and Advanced Topics
By
–
RAG Overview If you've been looking for a good overview of LangChain + RAG, then you're in luck! @sophiamyang recently released a FANTASTIC presentation on exactly that. Covers both the basics as well as more advanced topics Presentation: https://
sophiamyang.github.io/slides-langcha
in-rag-panel/
… -
Markov Chains: Why Walk When You Can Flow?
By
–
Markov Chains: Why Walk When You Can Flow? https://
bit.ly/3r1qd85
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Building RAG from Scratch for Your AI Product
By
–
"Why your next AI product needs RAG implemented in it" There are a LOT of different options for RAG But sometimes it's best to go back to the basics and build RAG from scratch @Avra_b wrote a fantastic article on why RAG is needed and how to get started, including a GitHub
-
Distinguishing Approximate Retrieval from Reasoning in LLMs
By
–
Do not confuse approximate retrieval with reasoning.
I used this scenario as a simple didactic example of physical understanding (or lack thereof).
Naturally, a pure text LLM will answer such questions correctly if the scenario, or a significantly similar one, is described in its -
Understanding RAG Dynamics: Retrieval Augmented Generation Explained
By
–
Watch this insightful video to learn more about the dynamics of RAG, Retrieval Augmented Generation: https://
youtu.be/7ytyK6u3aAk. -
RAG-Powered AI Tutor Surpasses ChatGPT Knowledge Limitations
By
–
The Towards AI's AI tutor uses Retrieval Augmented Generation (RAG), enabling both chatbot and user. Contrary to ChatGPT's limited knowledge, AI tutor pulls updated information from various sources for AI queries.