Accueil Explorer Aide
S'inscrire Connexion
OpenSource
/
ollama
2
0
Fork 0
Fichiers Tickets 0 Pull Requests 0 Wiki

Aucune description

Branche: jmorganca/llama-bump
Branches Tags
ollama
ZIP TAR.GZ
jmorganca f443dd7b81 llama: sync llama.cpp to commit 8962422 il y a 8 mois
.github a017cf2fea Split rocm back out of bundle (#6432) il y a 8 mois
api 8e6da3cbc5 update deprecated warnings il y a 8 mois
app 93ea9240ae Move ollama executable out of bin dir (#6535) il y a 8 mois
auth b732beba6a lint il y a 9 mois
cmd 5f7b4a5e30 fix(cmd): show info may have nil ModelInfo (#6579) il y a 8 mois
convert 9cfd2dd3e3 Merge pull request #6522 from ollama/mxyng/detect-chat il y a 8 mois
docs 741affdfd6 docs: update faq.md for OLLAMA_MODELS env var permissions (#6587) il y a 8 mois
envconfig 751009a5d7 Runtime selection of new or old runners il y a 8 mois
examples 0be8baad2b Update and Fix example models (#6065) il y a 9 mois
format b732beba6a lint il y a 9 mois
gpu f29b167e1a Use cuda v11 for driver 525 and older (#6620) il y a 8 mois
integration 21947d5c1b harden integration tests il y a 8 mois
llama f443dd7b81 llama: sync llama.cpp to commit 8962422 il y a 8 mois
llm f52d4b9879 Make new tokenizer logic conditional (#6395) il y a 8 mois
macapp 0e4d653687 upate to `llama3.1` elsewhere in repo (#6032) il y a 9 mois
openai 01d544d373 OpenAI: Simplify input output in testing (#5858) il y a 8 mois
parser b732beba6a lint il y a 9 mois
progress f7e3b9190f cmd: spinner progress for transfer model data (#6100) il y a 8 mois
readline 2697d7f5aa lint il y a 8 mois
scripts 0eabc2e34d remove unused script il y a 8 mois
server e1dfc757b3 revert llm changes il y a 8 mois
template 9468c6824a Merge pull request #6534 from ollama/mxyng/messages il y a 8 mois
types 0a8d6ea86d Fix typo and improve readability (#5964) il y a 8 mois
util cb42e607c5 llm: speed up gguf decoding by a lot (#5246) il y a 10 mois
version 2c7f956b38 add version il y a 1 an
.dockerignore 5017a15bcb add `macapp` to `.dockerignore` il y a 1 an
.gitattributes 3d1f3569cf update `.gitattributes` il y a 8 mois
.gitignore 01ccbc07fe replace static build in `llm` il y a 8 mois
.gitmodules fac9060da5 Init submodule with new path il y a 1 an
.golangci.yaml 8e6da3cbc5 update deprecated warnings il y a 8 mois
.prettierrc.json 8685a5ad18 move .prettierrc.json to root il y a 1 an
CONTRIBUTING.md 8200c371ae add `CONTRIBUTING.md` (#6349) il y a 8 mois
Dockerfile 9df5f0e8e4 Reduce docker image size (#5847) il y a 8 mois
LICENSE df5fdd6647 `proto` -> `ollama` il y a 1 an
README.md 50c05d57e0 readme: add Painting Droid community integration (#5514) il y a 8 mois
SECURITY.md 463a8aa273 Create SECURITY.md il y a 9 mois
go.mod feedf49c71 Go back to a pinned Go version il y a 8 mois
go.sum 9b6c2e6eb6 detect chat template from KV il y a 10 mois
main.go b732beba6a lint il y a 9 mois

README.md

 ollama

Ollama

Discord

Get up and running with large language models.

macOS

Download

Windows preview

Download

Linux

curl -fsSL https://ollama.com/install.sh | sh

Manual install instructions

Docker

The official Ollama Docker image ollama/ollama is available on Docker Hub.

Libraries

Quickstart

To run and chat with Llama 3.1:

ollama run llama3.1

Model library

Ollama supports a list of models available on ollama.com/library

Here are some example models that can be downloaded:

Model Parameters Size Download
Llama 3.1 8B 4.7GB ollama run llama3.1
Llama 3.1 70B 40GB ollama run llama3.1:70b
Llama 3.1 405B 231GB ollama run llama3.1:405b
Phi 3 Mini 3.8B 2.3GB ollama run phi3
Phi 3 Medium 14B 7.9GB ollama run phi3:medium
Gemma 2 2B 1.6GB ollama run gemma2:2b
Gemma 2 9B 5.5GB ollama run gemma2
Gemma 2 27B 16GB ollama run gemma2:27b
Mistral 7B 4.1GB ollama run mistral
Moondream 2 1.4B 829MB ollama run moondream
Neural Chat 7B 4.1GB ollama run neural-chat
Starling 7B 4.1GB ollama run starling-lm
Code Llama 7B 3.8GB ollama run codellama
Llama 2 Uncensored 7B 3.8GB ollama run llama2-uncensored
LLaVA 7B 4.5GB ollama run llava
Solar 10.7B 6.1GB ollama run solar

[!NOTE] You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.

Customize a model

Import from GGUF

Ollama supports importing GGUF models in the Modelfile:

  1. Create a file named Modelfile, with a FROM instruction with the local filepath to the model you want to import.

    FROM ./vicuna-33b.Q4_0.gguf

  2. Create the model in Ollama

    ollama create example -f Modelfile

  3. Run the model

    ollama run example

Import from PyTorch or Safetensors

See the guide on importing models for more information.

Customize a prompt

Models from the Ollama library can be customized with a prompt. For example, to customize the llama3.1 model:

ollama pull llama3.1

Create a Modelfile:

FROM llama3.1

# set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1

# set the system message
SYSTEM """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
"""

Next, create and run the model:

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

For more examples, see the examples directory. For more information on working with a Modelfile, see the Modelfile documentation.

CLI Reference

Create a model

ollama create is used to create a model from a Modelfile.

ollama create mymodel -f ./Modelfile

Pull a model

ollama pull llama3.1

This command can also be used to update a local model. Only the diff will be pulled.

Remove a model

ollama rm llama3.1

Copy a model

ollama cp llama3.1 my-model

Multiline input

For multiline input, you can wrap text with """:

>>> """Hello,
... world!
... """
I'm a basic program that prints the famous "Hello, world!" message to the console.

Multimodal models

ollama run llava "What's in this image? /Users/jmorgan/Desktop/smile.png"
The image features a yellow smiley face, which is likely the central focus of the picture.

Pass the prompt as an argument

$ ollama run llama3.1 "Summarize this file: $(cat README.md)"
 Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.

Show model information

ollama show llama3.1

List models on your computer

ollama list

Start Ollama

ollama serve is used when you want to start ollama without running the desktop application.

Building

See the developer guide

Running local builds

Next, start the server:

./ollama serve

Finally, in a separate shell, run a model:

./ollama run llama3.1

REST API

Ollama has a REST API for running and managing models.

Generate a response

curl http://localhost:11434/api/generate -d '{
  "model": "llama3.1",
  "prompt":"Why is the sky blue?"
}'

Chat with a model

curl http://localhost:11434/api/chat -d '{
  "model": "llama3.1",
  "messages": [
    { "role": "user", "content": "why is the sky blue?" }
  ]
}'

See the API documentation for all endpoints.

Community Integrations

Web & Desktop

Terminal

Database

Package managers

Libraries

Mobile

Extensions & Plugins

Supported backends

  • llama.cpp project founded by Georgi Gerganov.