Fully local Video Summaries with llama3 on ollama. Breaks up longer videos into chunks and provides a summary. Lots of questions on the last vid so here i am fixing errors real time.

Open-source: git.new/local-vid-summ…

L4, L40S, V100, and more are available directly through the platform with dedicated vCPUs and up to 96GB of RAM. 🔥

In 60 secs, you can run any Docker Build Cloud is here! 🐳🧱☁️ container with GPUs using the CLI, API, or dashboard. Spawn your favorite LLMs with ollama in one call. 🚀

ollama run llama3-gradient

AI Town 1 Click Launcher

One of the coolest AI projects I've tried, by the AI team at a16z, where a bunch of AI characters interact with one another in a persistent universe, and I can also join as a character.

Supports Mac & Linux (No Windows), only prerequisite is ollama.

- clickhouse local (ClickHouse)
- llm (@simonw)
- ollama (@ollama)
- llama 3 8b q8 (@AIatMeta)

w/ an apple health file converted to .parquet
using 🌌 expanse (github.com/tosh/expanse)

🧙‍♀️🪄 witchery!

Eric Hartford Kugs Wing Lian (caseus) ollama It's here! ollama.com/library/dolphi…

Small trick for ollama 👋
If you prefer q5_K_M as quantization, but you like having it as default model. i.e. llama3:latest --> q5_K_M

ollama pull llama3:8b-instruct-q5_K_M
ollama cp llama3:8b-instruct-q5_K_M llama3

That's it! Quick and Easy.

Native AI support now available in Edge Functions

Cool stuff 👇 to try out this weekend ….

Team!

Show off your cool open-source AI projects? (bonus if local & private)

Let's make this thread happen!!! Reply below with your project. 🧵

Let's go open-source!

If you use Ollama, you have your 100% private 'AI Internet' running INSIDE your computer.

You can verify this easily. Simply turn off your wifi and try running an inference. Here I'm chatting with Lllama3 over Open WebUI (Formerly Ollama WebUI) with @Ollama while the WIFI is turned off.

Support the open-source community so little tech can grow!

Help Ollama & Friends!

github.com/ollama/ollama

Oh, I totally missed that we can now configure Cody AI to use a model hosted on ollama!

sourcegraph.com/blog/local-cod…

ollama run qwen:110b

ollama.com/library/qwen:1…

Local only AI town is ready w/ ollama Together AI and Convex!

Run an AI Town locally, powered by llama3 🎉

No cloud signups needed. Make your own world, and then talk to it :)

Runs the open-source Convex backend locally.
Use ollama locally or Together AI for cloud LLM. AI Town

Before we begin, take a look at what we're about to create!

As always, I'll be using my favourite stack:

- @Ollama for locally serving a LLM (Llama-3)
- @Llama_Index for orchestration
- @Streamlit for building the UI
- Lightning AI ⚡️ for development & hosting

Let's go! 🚀

No need for API keys to get started. No need for a credit card.

Your data belongs to you! Your choice of tooling.

Thank you for supporting open-source!

Come join us in Toronto on Thursday, May 2nd!

lu.ma/devs5

Space is limited, so please register soon.