-
Groq API Cookbook
Ready to cook? 🚀 Dive into this collection of example code and guides for the Groq API. To get started, you’ll need a free Groq API key, which you can obtain by creating an account here. Join Groq developer community on Discord! Here, we discuss useful tools, share guidance, and collaborate with industry professionals. Contributing…
-
Open Source AI News [29 Jul 2024]
What a massive week for Open Source AI. We finally managed to beat closed source fair and square! Stability dropped Sv4D, Nvidia released MambaVision, SakanaLabs with Evo (merging + stable diffusion), and more. This was a landmark week, and I’m personally quite happy with the direction of open source AI/ ML! Author: Vaibhav (VB) Srivastav…
-
Mistral Large 2
Today, Mistral announces Mistral Large 2, the next generation of its flagship model. Compared to its predecessor, Mistral Large 2 is significantly more capable in code generation, mathematics, and reasoning. It also provides much stronger multilingual support and advanced function calling capabilities. This latest generation continues to push the boundaries of cost efficiency, speed, and…
-
Future of Gen AI
It’ll be very interesting to see how Gen AI tools choose to evolve over the next 12 months. Will they start to look & function more like full suite editors, or stay unique tools that serve as an entry point for beginners / pathway to more advanced tooling? Right now gen AI tools like MJ,…
-
Llama 3.1 405B
Starting today, open source is leading the way. Meta introducing Llama 3.1 405b their most capable models yet. Today Meta releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama…
-
Nvidia Minitron 4B / 8B
Nvidia releases Minitron 4B & 8B – iteratively pruning and distilling 2-4x smaller models from large LLMs, requiring 40x fewer training tokens and with 16% improvement on MMLU! Distilled model (w/ pruning + retraining) beats teacher! Best practices: And many more in the paper below. Minitron 8B Base Minitron is a family of small language…
-
ElevenLabs Reader App (iOS / Android)
The ElevenLabs Reader App is now on iOS and Android. Choose from hundreds of high quality AI voices to narrate any article, PDF, or ePub on the go. It’s only available in the US, UK, and Canada today. The app will launch worldwide in the next few weeks once ElevenLabs Dev Team add support for…
-
RTVI-AI: Real-time Voice and Video Inference
Today Daily announcing an open standard for Real-time Voice and Video Inference: RTVI-AI. The RTVI abstractions and data structures define how client applications communicate with inference services. These are the “real-time APIs” for use cases like: Daily Team shipping open source reference JavaScript and React SDKs today, with iOS, Android and other platform SDKS coming…
-
Open Source AI News [Mon 22 July]
Probably the craziest week in Open Source AI (yet): There’s a lot more; Arcee (mergekit) released a series of LLMs, each better than the other, and Numina and HF Numina 72B (based on Qwen 2) and Math datasets, Mixbread with embedding models (english + german) and a lot more! It’s fun to see so many…
-
StockBot
@GroqInc is incredibly fast, currently up to 1200+ tokens/second. But what can you do with that speed? Introducing StockBot, a lightning fast AI chatbot powered by Llama3-70b on Groq that responds with live stock charts, financials, news, and screeners. All open source! StockBot is an app that leverages GroqInc’s speed, @vercel’s AI SDK, and @tradingview’s…