PaLM 2 (L) also does not outperform GPT-4 on an MMLU 5-shot, but it does outperform LLaMA-I, a fine-tuned model for LLaMA. Here's what I pulled from the technical reports for LLaMA, PaLM 2, and GPT-4.
LLMS
-
Small Language Models: 3B and 7B Parameters Emerge in Open Source
By
–
We are seeing a lot of models pop up in the 3B and 7B param range, incl RedPajamas-INCITE 3B from Together that is based on the RedPajamas dataset. That dataset is designed to replicate the LLaMA dataset. I've heard Meta is also exploring 3B as an option for its fully OSS model.
-
Google PaLM 2 Comes in Four Sizes with Mobile Capabilities
By
–
When it comes to PaLM 2, Google said it would come in four sizes. It didn't disclose parameter count, but it did give us some tea leaves to evaluate, the first of which is that Gecko (its smallest) can run on a mobile device offline.
-
LangChain Business Model and Google’s PaLM Announcement Analysis
By
–
Today's issue of Supervised is gonna cover two topics: first, LangChain and questions about its business; second, breaking down some of Google's PaLM announcement. https://
supervised.news/p/parrots-geck
os-and-frameworks-as
… -
Demystifying ChatGPT and The Future of Artificial Intelligence
By
–
Join us for the panel discussion "Demystifying ChatGPT and The Future of Artificial Intelligence" from @babcsf
, featuring @MarshallChoy SVP of Product at @SambaNovaAI The live event takes place May 17, 2023 from 6p – 8p in San Francisco, CA. Register at https://
babc.chambermaster.com/events/details
/demystifying-chatgpt-and-the-future-of-artificial-intelligence-presented-by-simmons-simmons-4915
… -
Microsoft Chief Scientific Officer Discusses LLMs Ethics AGI Regulation
By
–
Very insightful interview with @Microsoft
’s Chief Scientific Officer covering LLMs, government regulation, ethics and safety, AGI and more. -
AutoGPT as Proof of Concept Leading to Recursive Code Interpreter
By
–
AutoGPT is a PoC. The final form is probably code interpreter with recursion and will mostly happen inside chatGPT itself
-
Bing AI Evaluated as a Top Tool for Content Creators
By
–
7/ Bing AI (Powered by ChatGPT4): Impressive response with up-to-date info, thanks to its access to the Bing search index. Rating: #1. Its accurate and relevant information makes it the most valuable tool for content creators.
-
Evaluation of ChatGPT-4 performance and knowledge limitations
By
–
6/ ChatGPT-4: Gave a detailed response but relied on outdated information from its capped knowledge base. Rating: #2. Although it provided accurate info about beta testing, it didn't address the current state of TestingCatalog.