Function calling with Local Models 🦙🔥⚡️

Using ollama, Hermes2-llama3 by Teknium (e/λ) and llama3 by AI at Meta, we now have local models excelling at tool calls. Where will we be in 5 years when more powerful models are running at the edge.

code: git.new/ollama-tools

Open UI Local 1 Click Launcher

Open UI from Weights & Biases is a cool AI app that live-generates UIs. It's like Vercel's V0 but open source, and works with both ChatGPT & open source models via ollama

Make sure to check out MatthewBerman's tutorial, and run it with 1 click.

Im using Meta’s llama3, for a ChatGPT like tool, running local on my computer. Better for privacy.

To setup locally in Mac Terminal :

- ollama : ollama.com
- oterm : github.com/ggozad/oterm
- llama3 : llama.meta.com/llama3/

In the latest Cody for VS Code, we've made it easier than ever to use ollama models

As long as you have Ollama running, you'll see your downloaded models in VS Code!

You don't need to muck around in settings anymore to turn this on. Get Llama 3 for coding FAST 🚀

Ollama v0.1.34 is out!

Improvements on Ollama's memory management, specifically, how models are loaded and scheduled across all platforms.

Release notes:
github.com/ollama/ollama/…

...Ollama continues to catch and squish bugs. 🫡

William Antônio 😎

这个代码级别的 Ollama 架构解析，讲了不少 Ollama 在代码上的黑科技
blog.inoki.cc/2024/04/16/Oll…

Can local models do Autonomous RAG? I put Hermes2-Llama3 by Teknium (e/λ) to the test.

0 expectations but pleasantly surprised by how well it performs on ollama. I'll continue to improve the flow.

code: git.new/ollama-autorag

Went to an event... came home like this.

Committed to be there for developers.

Hermes2 Pro doing 3 parallel function calls and writing an article with the results. Exceptional work by Teknium (e/λ) and team. Cannot believe this is an 8b param model.

code: git.new/ollama-tools

introducing ollama-reply 🦙 a browser extension that uses ollama to generate smart replies for LinkedIn and X

👨‍🍳 customizable: use any model/adapt to your needs
🆓 open source: github.com/jose-donato/ol…

tech:
ollama + AI at Meta llama3
React
Tailwind CSS
shadcn + Radix

Groq & Ollama support now live in superwhisper. Along with Mute while recording and scrolling text result.

The speed of Groq is mindblowing.

The latest version update allows you to dynamically load .@Ollama models to Dialoqbase.

Here is an example using Phi3:latest to chat with a YouTube video.

Powered by LangChain

Time to abandon ChatGPT and run llama3 locally with Ollama. 🫡

*not that individuals can do much, to be fair

Thor 雷神 ⚡️ Does SupaCape count?

cooking smth in my free time

do your crypto analysis using an AI assistant with knowledge from top traders like adam Byzantine General

📈 prices from any exchange CCXT Library
🌎 TanStack tech
🎨 shadcn ui
🤖 ai LangChain + ollama

going to open source. wanna help? dm

基于 Flow Engineering + LLM 构建 「文生高清视频」的MoneyPrinterTurbo 开源，目前 10.7K Star ⭐️

1. 提供主题或关键词，就可以自动生成视频文案、素材、字幕、背景音乐，然后合成一个高清的短视频 💥
2. 支持Web 界面和 API 文档
3. 支持OpenAI、Ollama 私域模型👍

github.com/harry0703/Mone…

Run #llama3 8b (via #ollama ) on #RISCV mini laptop #LicheeConsole 4A~
About 6s/token, waiting for RVV optimization~

Fuck it. Dalai-Ollama.