That's a wrap! Every day, I share and simply content around Python, Data Science, Machine Learning & Large Language Models. Find me → @Sumanth_077 Like/RT the first tweet and help this reach more people.
LLMS
-
BPE algorithm’s longest tokens are banners and whitespace
By
–
It’s whatever the byte-pair encoding algorithm says which depends on the pre-train statistics. There are many shorter ones too — the top 130 longest tokens are all banners and whitespace of various lengths.
-
Dolma: A 3 Trillion Token Open-Source Training Dataset for LLMs
By
–
A 3 Trillion (yes, trillion) token open-source training dataset for LLMs: Dolma is built from a mixture of web content, scientific papers, code, public-domain books, social media, and encyclopedic materials. Now available on Huggingface if you have a spare 5.4 Terabytes
-
Google’s Gemini Product Roadmap and Potential Rebranding
By
–
If renaming is involved, Google is cooking something big! Here is what is on the radar: – Gemini Advanced (Pro subscription)
– Gemini Apps (Mobile version?)
– Gemini Motoko (Custom GPTs) TBH, most people expect Google to invent something completely new, but that doesn't seem to https://
x.com/evowizz/status
/evowizz/status/1753123550712488302
… -
House of Lords Select Committee Report on LLMs Released Today
By
–
House of Lords select committee report on LLMs out today. https://
committees.parliament.uk/publications/4
3172/documents/214762/default/
… Very impressed by the coverage and quality of these recommendations. -
Arc Browser Launches AI-Powered Search and Exploration Features
By
–
Arc browser introduced new AI-powered features.
— Rowan Cheung (@rowancheung) 2 février 2024
New to the browser are Instant Links to instantly visit top search results and an Explore tool that leverages LLMs to provide an integrated browsing and searching experience.
I've been loving it so far!https://t.co/dSVBT7Prg4Arc browser introduced new AI-powered features. New to the browser are Instant Links to instantly visit top search results and an Explore tool that leverages LLMs to provide an integrated browsing and searching experience. I've been loving it so far!
-
Google Upgrades Bard with Gemini Pro Model
By
–
The first of Google's AI upgrades is Gemini Pro, now running on Bard.
— Rowan Cheung (@rowancheung) 2 février 2024
Big improvement from the previous LaMDA and PaLM models.
This means Bard now has upgraded understanding, summarizing, reasoning, and coding capabilities. pic.twitter.com/IqWU9RFvHgThe first of Google's AI upgrades is Gemini Pro, now running on Bard. Big improvement from the previous LaMDA and PaLM models. This means Bard now has upgraded understanding, summarizing, reasoning, and coding capabilities.
-
Google Rolls Out Major AI Upgrades Across Bard Maps Imagen
By
–
Google just rolled out huge AI upgrades across Bard, Google Maps, and Imagen-2. Plus, huge developments in AI from Amazon, Sam Altman, Georgia Tech, Meta, Arc, and Anthropic. Here's everything you need to know:
-
Allen AI releases OLMo open language model with technical documentation
By
–
Technical Report: https://
allenai.org/olmo/olmo-pape
r.pdf
…
Blog: https://
blog.allenai.org/olmo-open-lang
uage-model-87ccfc95f580
…
Github: https://
github.com/allenai/OLMo
Models: -
AI2 Launches OLMo Open Language Model Framework
By
–
@allen_ai launched "OLMo: Open Language Model". AI2 opens its framework that provide access to data, training code, models, and evaluation code. The training data Dolma is also released, a dataset of 3 trillion tokens from a diverse mix of web content, academic