Ollama General Introduction
ollama is a lightweight framework for running native language models, allowing users to easily build and run large language models. It offers multiple quick start and installation options, supports Docker, and includes a rich set of libraries for users to choose from. It is easy to use, provides a REST API, and has a variety of plugins and extensions that integrate with the community.
ollama is a pure command line tool, personal computer use, recommended deployment of local chat interface, such as: Open WebUI, Lobe Chat, NextChat
Modify the default installation directory: https://github.com/ollama/ollama/issues/2859
Ollama Feature List
Getting Large Language Models Up and Running Fast
Support macOS, Windows, Linux systems
Provides libraries such as ollama-python, ollama-js, etc.
Including Llama 2. Mistral, Gemma et al. preconstructed model
Supports both local and Docker installations
Provide customized model function
Support for model conversion from GGUF and PyTorch
Provide CLI operation guide
Provide REST API support
Commonly used ollama commands
Pull model: ollama pull llama3.1
Run model: llama run llama3.1
Delete model: llama rm llama3.1
List all available models: ollama list
Query API service address: ollama serve (default http://localhost:11434/)
Ollama Help
Installation scripts and guides available through the ollama website and GitHub page
Installation using the provided Docker image
Model creation, pulling, removing and copying via CLI operations
Initialize and run local builds
Run the model and interact with it
Some of the models supported by Ollama
Model | Parameters | Size | Download |
---|---|---|---|
Llama 2 | 7B | 3.8GB | ollama run llama2 |
Mistral | 7B | 4.1GB | ollama run mistral |
Dolphin Phi | 2.7B | 1.6GB | ollama run dolphin-phi |
Phi-2 | 2.7B | 1.7GB | ollama run phi |
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 |
Llama 2 13B | 13B | 7.3GB | ollama run llama2:13b |
Llama 2 70B | 70B | 39GB | ollama run llama2:70b |
Orca Mini | 3B | 1.9GB | ollama run orca-mini |
Vicuna | 7B | 3.8GB | ollama run vicuna |
LLaVA | 7B | 4.5GB | ollama run llava |
Gemma | 2B | 1.4GB | ollama run gemma:2b |
Gemma | 7B | 4.8GB | ollama run gemma:7b |