説明なし

Jeffrey Morgan 8685a5ad18 move .prettierrc.json to root		1 年間前
app	8685a5ad18 move .prettierrc.json to root	1 年間前
docs	55898a3382 Move python docs to separate file	1 年間前
ollama	23c589d578 output confirmation after pull	1 年間前
.gitignore	d34985b9df add templates to prompt command	1 年間前
.prettierrc.json	8685a5ad18 move .prettierrc.json to root	1 年間前
Dockerfile	48920c873b add basic `Dockerfile`	1 年間前
LICENSE	df5fdd6647 `proto` -> `ollama`	1 年間前
README.md	55898a3382 Move python docs to separate file	1 年間前
models.json	76918ddb67 change name.json	1 年間前
poetry.lock	4d0eb7639a use ctransformers as backup to llama-cpp	1 年間前
pyproject.toml	f1d5036f1e v0.0.9	1 年間前
requirements.txt	4d0eb7639a use ctransformers as backup to llama-cpp	1 年間前

Ollama

Ollama is a tool for running large language models. It's designed to be easy to use and fast.

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.

Install

Using pip:

pip install ollama

Using docker:

docker run ollama/ollama

To run a model, use ollama run:

ollama run orca-mini-3b

You can also run models from hugging face:

ollama run huggingface.co/TheBloke/orca_mini_3B-GGML

Or directly via downloaded model files:

ollama run ~/Downloads/orca-mini-13b.ggmlv3.q4_0.bin