Released a free tool on ChatDB: Parquet AI
Query parquet files with natural language in the browser.
◆ Powered by
@duckdb
in the browser
◆ LLM from
@GroqInc
and Llama-3-70B
Here's me querying the capybara-dpo dataset from
@huggingface
🔥 Calling out UX critics
We're refining the experience at and we'd love to hear about your opinions/comments/ideas about the current experience and what could be better. We're interested in your thoughts about:
Ease to use to send a quick message to a…
If you missed our Chief Tech Evangelist,
@lifebypixels
speaking at
#ImagineAILive
, here's your chance to watch the recording of his presentation on powering
#GenAI
with our
#LPU
™ Inference Engine, which is better, faster and cheaper than GPUs.
Thanks
@benjaminwolba
for the opportunity to sit down and chat about
@GroqInc
and some of my own personal thoughts about the rising opportunity of AI and entrepreneurs. I hope it's helpful for those who read it. Cheers!
For everyone who's been asking for an Android app, here you go! Thank you
@omidaziz
for the fastest experience in the Android market.
Sign up for beta now!
Your own Copilot in VSCode lightning-fast thanks to Groq and Llama3
In this thread 🧵, I'll guide you through connecting
@GroqInc
with VSCode, unlocking the full potential of Llama 3 (
@AIatMeta
) as your Copilot👇
Developers and companies are seeking lower latency and greater throughput for their generative & conversational AI applications. We're thrilled to have
@Petie_P
on our team to to unlock business value for Groq customers with the world's fastest inference engine.
I found a new tool calling champion
Llama3 70b on
@GroqInc
Challenge: given user query, extract financial quarters and years.
Example: "How did revenue change between Q4 2023 and year before that?"
The 70b model:
• passed the task
• was very fast
• had best pricing
I…
@GroqInc
@tim_keary
Makes total sense. It's doing something that other companies are not.
After I saw the Llama 3 + Groq combo, I saw a new form of AI.
"Groq has rapidly become one of the most exciting providers in the LLM market and is in a solid position to be a key enabler of AI model development in the future." --
@tim_keary
We're excited to co-sponsor the first-ever Llama 3 hackathon at SHACK15 in San Francisco May 11-12. We can't wait to meet everyone, present a speaker workshop, participate in the judging, and see what the developer community can build with the Groq API.
Tune in tomorrow to hear how to optimally utilize custom precision arithmetic units in modern leading compute chips such as the Groq LPU. The presentation by Oskar Mencer, CEO of
@MaxelerTech
, will be available to the general public.