Unify

Very excited to release our Model Hub 😍 - a collection of LLM endpoints with live runtime benchmarks all plotted across time 📈 We currently have 21 models provided by: Anyscale, Perplexity, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with many more on the roadmap. We test across different regions (Asia, US, Europe), with varied concurrency and sequence length. By plotting across time, our dashboard highlights the stability and variability of the different endpoints, and their ongoing evolution across API updates and system changes. Our benchmarking code is open source: https://lnkd.in/ggt_-pRZ Our unified API also makes it very easy to test and deploy these different endpoints in production, without needing to create several accounts 🔑 Our Hub is a work in progress, and we will be releasing new features every week 🚀 We are granting everyone $5 starting credits with a free top up of $2.50 every week, compatible with all major LLM providers (more coming soon!). You can sign up here [https://console.unify.ai/]. Please tell us what you think, and we’ll quickly incorporate feedback into the next weekly release! 😊 Check out our launch video, where we show how to build a simple chatbot on top of the different LLM providers 🤖 https://lnkd.in/gbzCsahN As always - let’s unify AI! 🟢💪

We’re excited to announce Ivy is partnering with Kornia, allowing Kornia to be used with TensorFlow, JAX, and NumPy for the first time! You can use the new `kornia.to_tensorflow()`, `kornia.to_jax()` and `kornia.to_numpy()` methods, which take advantage of Ivy’s transpiler, to use Kornia in your framework of choice. Try it out now in the latest Kornia version! (0.7.4) https://lnkd.in/eKu_PF88 Ivy on GitHub: https://lnkd.in/eTVJx9WH Ivy Demos: https://lnkd.in/e7fD-QEn #ml #ai #machinelearning #pytorch #jax #tensorflow #numpy

Incredibly flattered that Amazon have invited me to be their keynote speaker for this year's AWS Gen AI Loft event. Can't wait! ❤️ I'll be sharing my thoughts on why Gen AI still feels like it's stuck in first gear, what some of the biggest challenges are, and how we can all take steps to migitate these, and get our apps finally flying 🛸 (Hint: from our perspective, thoughtful evals and your data flywheel are essential ingredients 🔁) If you'll be in London on October 3rd, you can sign up here: https://lnkd.in/eNnpB3U6 See you there! ✌️

It's official! The AWS GenAI Loft Tour is coming to London. On October 3rd, we’re hosting the AWS GenAI Showcase: Discover the Top Innovative Startups Building on AWS. Hear insights from our keynote speaker Unify CEO, Daniel Lenton, on optimising for quality, speed, and cost-efficiency when leveraging LLMs. Learn how to extract maximum value from these powerful AI tools and drive transformative results for your business. Rod Carr, the Head of Industry for Retail at AWS, will lead a panel with seasoned retail professionals on the root causes of shrinkage and how to leverage innovative technology to enhance inventory visibility and security. We’ll get to see innovative demonstrations by Philip Ashton from 7bridges, Ben Hookway from Relative Insight, Jenn Cunningham and Becky Kershaw from PolyAI and Silke Zetzsche from AudioStack. Sign up here: https://lnkd.in/e7MvrdyW Unify Relative Insight PolyAI 7bridges AudioStack Tricia Troth Ina Yulo Stuve Harumi Hirata Palacios Nicolas Tarducci Sinan Erdem Leon Rees Kim Moloney Antonia Secelean

Open AI released the new model O1 and I tested and compared it's logical thinking capabilities with Claude 3.5 Sonnet using Unify I prompted both of them with a mathematical riddle which required some calculations and guess who won? Puzzle: Hansa ate a meal at Jugju hotel costing Rs.210. He gave the manager a Rs. 1000 note. He kept the change, came back a few minutes later and had some food packed for his girl friend 'Hansi'. He gave the accountant a Rs. 500 note and received Rs. 120 in change. Later the bank told the accountant that both the Rs. 1000 and the Rs. 500 notes were counterfeit. How much money did the restaurant lose? Ignore the profit of the food restaurant. Check it out 👇

We’re excited to have Xiaoyi Chen from Indiana University Bloomington, co-author of the paper "The Janus Interface: How Fine-Tuning in Large Language Models Amplifies Privacy Risks," joining us this Friday for our Paper Reading Session! RSVP👉 https://lu.ma/jok7bp2m The research introduces a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs. It also formalizes the privacy leakage problem in LLMs and explains why forgotten PIIs can be retrieved through empirical analysis of open-source language models 🧠👩💻 Check out the Paper👉 https://lnkd.in/gDGH6Gcv See you there!

We are excited to welcome everyone to our self-hosted Paper Reading Session where we’ll discuss the paper "Efficient Guided Generation for Large Language Models". Happening next Friday (August 23rd)! RSVP 👉 https://lu.ma/4xo831vi The research introduces a powerful framework for guiding text generation using regular expressions and context-free grammar, enabling the creation of an index over a language model's vocabulary. This model-agnostic approach enforces domain-specific rules, ensuring reliable and structured text output 🧠 👨💻 Check out the Paper👉 https://lnkd.in/gqGqDzTD See you there!

We're thrilled to announce that Vapi will be joining us for our weekly Webinar Series tomorrow! (Wednesday)🤩 RSVP here👉 https://lu.ma/cke3hpft Join us as we welcome Sahil Suman, Solution Engineer at Vapi AI, to the session. Discover how VAPI enables the quick setup of high-quality voice agents and see the integration of Unify with VAPI for seamless access to various models and providers. See you there! 👩💻 Explore Vapi: ⚡ https://vapi.ai ⚡ https://github.com/VapiAI

Thanks for having me last night Amazon Web Services (AWS)! ❤️ Especially enjoyed hearing from Ben Lingwood about PwC's experience deploying GenAI, and learning how Lewis James has used LLMs to generate content on a huge scale at Reach plc. Honour to be a part of the discussion! See you at the next one ✌

We are really excited to welcome Zilong Wang from UC San Diego, who co-authored the paper "Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting". Happening Tomorrow! 🤩 RSVP👉 https://lu.ma/zesezv3u The research introduces SPECULATIVE RAG, a framework that leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM 🧠 Check out the Paper👉 https://lnkd.in/e3c8HJu4 See you there!