Ollama

Great article from Kelly showing how to get the most out of Granite Code with Ollama and Continue!

We at Qualcomm are taking edge AI to the next level by empowering developers with Ollama an open-source solution for seamless AI inference on Snapdragon X Series devices. By open-sourcing models and focusing on efficiency, developers can now - Run state-of-the-art models locally on edge devices -📱 Build faster, more efficient AI-powered applications -🔋 Optimize performance while reducing latency and power consumption Read our blog to know how we are bringing the power of LLMs on-device with Ollama https://lnkd.in/gUq4ayrh #ollama #AI #EdgeAI #MachineLearning #Snapdragon #Qualcomm #Developers #Innovation #OpenSource

❤️ You can now run models on 🤗 Hugging Face with Ollama 🦙 Let's go open-source and Ollama! 🚀🚀🚀

🚀 Ollama now available on Snapdragon X Series Our mission to deliver the ultimate developer experience on Snapdragon X Series platforms begins by partnering with leading AI tool providers, making AI accessible to all and empowering everyone to run large language models (LLMs) directly on their devices. Ollama is one such open-source project that serves as a powerful and user-friendly platform for running LLMs on-device. It provides the capabilities for developers to easily run these cutting edge models on-device and provides them with the right tools to create their own customizable AI experiences. With the recent announcements from AI at Meta around Llama 3.2, we have worked closely with Michael Chiang and the Ollama team to bring Llama3.2 support on our Qualcomm Snapdragon X Series platforms to all classes of developers. Get started by downloading and using Ollama with the Llama 3.2 models directly on your Snapdragon X Series devices here: https://lnkd.in/g3WPbEXx Learn more about the Llama3.2 support on Snapdragon X Series devices here: https://lnkd.in/g6cgUeku #AI #deeplearning #qualcomm #ollama #snapdragon Manish Sirdeshmukh Manoj Khilnani FRANCISCO CHENG Chun-Po Chang

Bespoke Labs released Bespoke-Minicheck, a 7B fact-checking model is now available in Ollama! It answers with Yes / No and you can use it to fact check claims on your own documents. How to use the model with examples: https://lnkd.in/gD9_9mCw

As an interest signal, #github stars don't tell the whole story, but.. they do tell a story. Here's a "star slope" comparison of two very popular #golang projects. Guess which is #genai?

I like my new keychain 🦙Thanks, Ollama 😊 If you’d like to learn more about building LLM-powered applications with Ollama and Java, check out this repository with tons of examples and use cases: https://lnkd.in/dH6QbUC4

Ollama is now supporting LLaMA 3.1 Meta. I'm implementing it for Coding, Sentiment Analysis, and Question Answering. Check out my GitHub for the latest developments and see how you can use LLaMA 3.1 for your projects! https://lnkd.in/gBfcY3J3

Just tried Ollama with Llama3.1. It's really amazing for testing your LangChain application. It's 8B params version easily ran on my MacBook Air M1 base version. So if you are just starting out with LLMs and want to try out open source LLMs like Llama3.1 locally without spending for API calls, give it a try...

It's pretty wild that you can now run a 405b model on your own hardware. Meta is just killing it with these models.