暫無描述

Patrick Devine 206fab0e15 add license layers to the parser		1 年之前
api	68df36ae50 fix pull 0 bytes on completed layer	1 年之前
app	280fbe8019 app: use `llama2` instead of `orca`	1 年之前
cmd	a6d03dd510 Merge pull request #110 from jmorganca/fix-pull-0-bytes	1 年之前
docs	9310ee3967 First stab at a modelfile doc	1 年之前
examples	3e10f902f5 add `mario` example	1 年之前
format	5bea29f610 add new list command (#97)	1 年之前
llama	40c9dc0a31 fix multibyte responses	1 年之前
parser	206fab0e15 add license layers to the parser	1 年之前
scripts	4dd296e155 build app in publish script	1 年之前
server	206fab0e15 add license layers to the parser	1 年之前
web	820e581ad8 web: fix typos and add link to discord	1 年之前
.dockerignore	6292f4b64c update `Dockerfile`	1 年之前
.gitignore	7c71c10d4f fix compilation issue in Dockerfile, remove from `README.md` until ready	1 年之前
.prettierrc.json	8685a5ad18 move .prettierrc.json to root	1 年之前
Dockerfile	7c71c10d4f fix compilation issue in Dockerfile, remove from `README.md` until ready	1 年之前
LICENSE	df5fdd6647 `proto` -> `ollama`	1 年之前
README.md	d14785738e README typo fix (#106)	1 年之前
ggml-metal.metal	e64ef69e34 look for ggml-metal in the same directory as the binary	1 年之前
go.mod	5bea29f610 add new list command (#97)	1 年之前
go.sum	5bea29f610 add new list command (#97)	1 年之前
main.go	1775647f76 continue conversation	1 年之前
models.json	5028de2901 update vicuna model	1 年之前

Ollama

Create, run, and share self-contained large language models (LLMs). Ollama bundles a model’s weights, configuration, prompts, and more into self-contained packages that run anywhere.

Note: Ollama is in early preview. Please report any issues you find.

Download

Download for macOS on Apple Silicon (Intel coming soon)
Download for Windows and Linux (coming soon)
Build from source

Examples

Quickstart

ollama run llama2
>>> hi
Hello! How can I help you today?

Creating a custom model

Create a Modelfile:

FROM llama2
PROMPT """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.

User: {{ .Prompt }}
Mario:
"""

Next, create and run the model:

ollama create mario -f ./Modelfile
ollama run mario
>>> hi
Hello! It's your friend Mario.

Model library

Ollama includes a library of open-source, pre-trained models. More models are coming soon.

Model	Parameters	Size	Download
Llama2	7B	3.8GB	`ollama pull llama2`
Orca Mini	3B	1.9GB	`ollama pull orca`
Vicuna	7B	3.8GB	`ollama pull vicuna`
Nous-Hermes	13B	7.3GB	`ollama pull nous-hermes`

Building

go build .

To run it start the server:

./ollama server &

Finally, run a model!

./ollama run llama2

README.md