ollama/README.md

45 lines
750 B
Markdown
Raw Normal View History

2023-06-27 12:08:52 -04:00
# Ollama
2023-06-22 12:45:31 -04:00
A fast runtime for large language models, powered by [llama.cpp](https://github.com/ggerganov/llama.cpp).
2023-06-27 17:13:07 -04:00
2023-06-30 11:39:24 -04:00
> _Note: this project is a work in progress. Certain models that can be run with `ollama` are intended for research and/or non-commercial use only._
2023-06-28 09:57:36 -04:00
## Install
2023-06-22 12:45:31 -04:00
Using `pip`:
2023-06-22 12:45:31 -04:00
```
2023-06-27 12:08:52 -04:00
pip install ollama
2023-06-22 12:45:31 -04:00
```
Using `docker`:
2023-06-30 12:31:00 -04:00
```
docker run ollama/ollama
```
2023-06-28 09:57:36 -04:00
## Quickstart
2023-06-25 13:08:03 -04:00
2023-06-29 18:25:02 -04:00
To run a model, use `ollama run`:
```
ollama run orca-mini-3b
2023-06-25 13:08:03 -04:00
```
2023-06-29 18:25:02 -04:00
You can also run models from hugging face:
2023-06-27 12:08:52 -04:00
2023-06-29 18:25:02 -04:00
```
ollama run huggingface.co/TheBloke/orca_mini_3B-GGML
```
2023-06-28 09:57:36 -04:00
2023-06-29 18:25:02 -04:00
Or directly via downloaded model files:
```
ollama run ~/Downloads/orca-mini-13b.ggmlv3.q4_0.bin
2023-06-28 09:57:36 -04:00
```
2023-06-27 13:46:46 -04:00
## Documentation
- [Development](docs/development.md)
2023-07-01 17:54:29 -04:00
- [Python SDK](docs/python.md)