https://github.com/fabricio872/local-llama

Simple script to run llama2 LLM locally on CPU
https://github.com/fabricio872/local-llama

Last synced: about 2 months ago
JSON representation

Simple script to run llama2 LLM locally on CPU

• Host: GitHub
• URL: https://github.com/fabricio872/local-llama
• Owner: Fabricio872
• License: mit
• Created: 2024-03-10T10:57:49.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-03-10T11:26:13.000Z (11 months ago)
• Last Synced: 2024-03-10T12:27:38.541Z (11 months ago)
• Language: Shell
• Size: 1.95 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# local-llama

Simple script to run llama2 LLM locally on CPU using this docker container as a base https://github.com/aborroy/llama2-docker-multiarch

## Installation

- install [Docker](https://www.docker.com/)

- run this command to integrate shell script 

```shell

sudo curl -o /usr/local/bin/llama https://raw.githubusercontent.com/Fabricio872/local-llama/main/llama

```

- set permission 

```shell

sudo chown $USER /usr/local/bin/llama && chmod +x /usr/local/bin/llama

```

## Usage

> Note that first run will take longer and will require internet connection to download docker container

```shell

llama "hello llama"

```