42998d797d
* remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm |
||
|---|---|---|
| .. | ||
| assets | ||
| src | ||
| .eslintrc.json | ||
| .gitignore | ||
| forge.config.ts | ||
| package-lock.json | ||
| package.json | ||
| postcss.config.js | ||
| README.md | ||
| tailwind.config.js | ||
| tsconfig.json | ||
| webpack.main.config.ts | ||
| webpack.plugins.ts | ||
| webpack.renderer.config.ts | ||
| webpack.rules.ts | ||
Desktop
This app builds upon Ollama to provide a desktop experience for running models.
Developing
First, build the ollama binary:
cd ..
go build .
Then run the desktop app with npm start:
cd app
npm install
npm start