AJR/TechradarDev
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs: add ollama

Browse Source
This commit is contained in:
Daniel
2024-06-05 10:22:16 +02:00
committed by Stefan Rotsch
parent 301c1e3d34
commit ffd7b9559b
3 changed files with 18 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
radar/2024-06-01/ollama.md Normal file
View File

@@ -0,0 +1,16 @@
---
title: "Ollama"
ring: trial
quadrant: tools
tags: [ai, coding]
---
Running large language models local?
Downloading [Ollama](https://ollama.com/download) and typing `ollama run llama3` is all you need.
Ollama is great to run various open source (open weight) models local and interact with them. You can do this either via the command line or via the [Ollama API](https://github.com/ollama/ollama/blob/main/docs/api.md).
Ollama takes care of downloading and running models and it supports the specification of own model packages in a "Modelfile".
At AOE, we use it for local development and testing.