Comment by sarthaksaxena
1 month ago
I have built npm for LLM models, which lets you install & run 10,000+ open sourced large language models within seconds. The idea is to make models installable like packages in your code:
llmpm install llama3
llmpm run llama3
You can also package large language models together with your code so projects can reproduce the same setup easily.
Also, is there is way I can invoke the models or is there an API which your tool exposes?
Yes indeed there is, run `llmpm serve <model_name>`, which will expose an API endpoint http://localhost:8080/v1/chat/completions & also host a chat UI where you can interact with the local running model https://localhost:8080/chat.
Follow the docs here: https://www.llmpm.co/docs
Pro tip for your use case: Checkout the `llmpm serve` section
Looks crazy! Thanks for building it, there is indeed a need for a npm or pip like package manager for AI Models.
Yeah :)! Just run `llmpm init` to start packaging your models along with your code.