RidgeRun.ai
@RidgeRunAI
Followers
29
Following
15
Media
39
Statuses
130
Computer Vision and Analytics
Minnesota, USA
Joined September 2022
The Metis M.2 lived up to the hype! We're excited to explore its full potential in upcoming projects. Kudos to the @AxeleraAI team for their constant releases and their quick support.
Great work from @ridgerunai getting the Metis M.2 AI accelerator running on Raspberry Pi 5 ๐ฅ. They break down setup, deployment with Voyager SDK & real-world benchmarks. Great guide if youโre into embedded AI, or looking for someone to help with your AI project/build ๐.๐
0
2
7
The result? ๐๐๐ป๐ถ๐ฝ๐ฒ๐ฟ outperforms GPT-4o in our function-calling tasks and other standard benchmarks, all while running efficiently on limited hardware. ๐.
0
0
0
LLMs excel at function calling, but theyโre often too resource-intensive for edge devices. In our latest blog post we share how we fine-tuned a compact, local model: ๐๐๐ป๐ถ๐ฝ๐ฒ๐ฟ, to perform reliable tool invocation.
ridgerun.ai
This post will take you through our journey on how we fine-tuned a model for function calling.
1
0
1
Ready to play with out new @AxeleraAI Metis M.2 board ๐. Stay tuned for the full walkthrough!
1
3
8
One of the most exciting mergers of history. @OpenAI to be merged with Jonny Ive's company: IO.
0
0
1
๐ Automate 2025 is here! ๐คโจ. Weโre excited to be part of the Automate Show this week! Come meet the team and see how our cutting-edge AI solutions can supercharge your next project. ๐ก๐ป. ๐ Want to chat? Letโs connect โ our engineers are ready to meet
0
0
1
A few months ago @AnthropicAI announced the Model Context Protocol: an open standard to interconnect language models with external tools and data sources. Learn how to build your own MCP server in our most recent post:.
ridgerun.ai
Discover how to build a simple MCP server in Python to manage a to-do list example using the Model Context Protocol (MCP). This step-by-step guide walks you through creating the server, connecting it...
0
0
1
Just in! @NVIDIAAI just took back the speech transcription leaderboard ๐! Their newest model parakeet-tdt-0.6b-v2 ๐ฆ, not only has the lowest word error rate, but has a commercial friendly license!. Try it out in our HuggingFace space ๐ค.
huggingface.co
0
1
1
Did you know you can use OpenAI's Python ๐ API to interact with models hosted locally in your computer? Thanks to Ollama, you can keep your conversations private, offline and secure. Learn how achieve this in our developer's blog๐:.
ridgerun.ai
Easily switch between OpenAI and local LLMs like Ollama using the same API! This post shows how to wrap the OpenAI Python (and JavaScript) client to talk to Ollama with minimal changes, letting you...
0
0
1
Did you miss the #AIIndex2025? No worries! Here's a 10 slide summary of the state of the AI market in 2025, courtesy of @StanfordHAI . Are you ready to add #AI to your project? Let's talk!.
linkedin.com
By Nestor Maslej The 2025 AI Index Report, published on April 7, 2025, is an independent initiative at the Stanford Institute for Human-Centered Artificial Intelligence (HAI), led by the AI Index...
0
0
1
"Pre-training as we know it will end" - Ilya Sutskever. Agentic systems are LLMs with superpowers, and a step in the direction of building truly autonomous systems. Check out @OpenAI guide to building agents:.
0
0
2
Our friends at @seeedstudio studio are hosting this #InteractiveSignage contest. Are you up for the challenge?.
Calling all makers to join our #InteractiveSignage Contest 2025! Inviting you to explore how smart tech, #IoT, and #AI can transform signs into experiences, making spaces more efficient, comfortable, and engaging. Submit your project to win $3,000 + and get featured in the smart
0
1
2
Another framework to build agentic systems! Now by @GoogleAI @googledevs . Empower your LLMs with orchestration and tooling ๐ค. Can't wait to try it out!.
๐ซ Simplify your AI agent development. Google's new open-source Agent Development Kit (ADK) is designed for effortless multi-modal and multi-agent systems. Get started โ
0
0
1
Llama 4 is finally out! Multimodal mixture of experts with massive context sizes. Thank you @AIatMeta !.
Today is the start of a new era of natively multimodal AI innovation. Today, weโre introducing the first Llama 4 models: Llama 4 Scout and Llama 4 Maverick โ our most advanced models yet and the best in their class for multimodality. Llama 4 Scout.โขย 17B-active-parameter model
0
0
1
Have you considered creating a custom ChatBot to effortlessly answer questions about your company's internal knowledge base? ๐ค๐ฌ. At we developed an on-premise Retrieval Augmented Generation (RAG) system from scratch and documented our journey for you.
ridgerun.ai
AI, Computer Vision and Machine Learning for your Audio and Video Projects. RidgeRun Artificial Intelligence provides cutting-edge machine learning consulting services and products for audio and...
0
0
1
"The AI Biology of LLMs". Two new wonderful papers by @AnthropicAI following their journey to understand mechanistic interpretability of language models. If you've ever read the series, you know these are great.
New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claudeโs (often complex and surprising) internal mechanisms.
0
0
1
๐ค Itโs always a pleasure to share the stage with our partners!. Big thanks to @AXIOMTEKUSA for joining us at NVIDIA GTC 2025 โ weโre proud to collaborate with you! ๐โจ. #GTC25 #GTC2025
0
0
0
The pace is incredible! @GoogleDeepMind just released their most intelligent model: Gemini 2.5 ๐ง . It's already crushing benchmarks!.
Think you know Gemini? ๐ค Think again. Meet Gemini 2.5: our most intelligent model ๐ก The first release is Pro Experimental, which is state-of-the-art across many benchmarks - meaning it can handle complex problems and give more accurate responses. Try it now โ
0
0
1