https://github.com/clebert/switch-llm
A macOS application to run local models like Mistral, with the option to enhance conversations by switching to GPT-4.
https://github.com/clebert/switch-llm
Last synced: 10 months ago
JSON representation
A macOS application to run local models like Mistral, with the option to enhance conversations by switching to GPT-4.
- Host: GitHub
- URL: https://github.com/clebert/switch-llm
- Owner: clebert
- License: mit
- Created: 2024-02-26T10:03:40.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-13T19:06:56.000Z (about 2 years ago)
- Last Synced: 2025-02-24T16:05:09.820Z (over 1 year ago)
- Language: TypeScript
- Homepage:
- Size: 2.23 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Switch LLM
> A macOS application to run local models like Mistral, with the option to enhance conversations by
> switching to GPT-4.
## Prerequisites
- macOS 14 (ARM)
- Node.js 20+
- Zig 0.12.0 (master)
## Getting started
Install npm dependencies:
```sh
npm install
```
Build the app:
```sh
npm run build
```
Start the app:
```sh
npm start
```
Download a model file in [GGUF](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md) format
from Hugging Face:
```sh
curl -L -o mistral-7b-instruct-v0.2.Q8_0.gguf https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q8_0.gguf
```