* chore(deps): update ollama/ollama docker tag to v0.6.2 * Update app version [skip ci] --------- Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com> Co-authored-by: github-action update-app-version <githubaction@githubaction.com> |
||
|---|---|---|
| .. | ||
| 0.6.2 | ||
| README.md | ||
| README_en.md | ||
| data.yml | ||
| logo.png | ||
README_en.md
Ollama
Ollama is an open-source large language model service that provides an API interface and chat interface similar to OpenAI. It allows seamless deployment of the latest GPT models and usage through APIs. It supports hot-loading model files, enabling model switching without restarting.
Quick Start
Access the
Containerslist, find the Ollama container, and open the terminal to chat with DeepSeek R1:
ollama run deepseek-r1:1.5b
Model Library
Ollama supports a variety of models available at ollama.com/library.
Note: You should have at least 8 GB of available RAM to run 7B models, 16 GB for 13B models, and 32 GB for 33B models.