6
GPT4All is a free-to-use, locally running, privacy-aware large language model that is a 3GB - 8GB file that you can download and query. No GPU or internet required (github.com)
submitted 3 years ago by to c/auai@programming.dev
6 comments fedilink hide all child comments
 

Wanted to share a resource I stumbled on that I can't wait to try and integrate into my projects.

A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. Nomic AI supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.

all 6 comments

sorted by: hot top controversial new old
[โ€“] 6 points 3 years ago* (last edited 3 years ago)

I'm still waiting for a local autonomous AI agent with search. I don't understand why most autonomous agent projects use GPT-4 without incorporating search capabilities. Allowing the model to continuously hallucinate is not productive. Instead, it should be able to discover factual information and perform genuinely useful tasks.

  • permalink
  • fedilink
  • source
    •
    [โ€“] 2 points 3 years ago (1 child)

    I've got this running. And it's fun!

    But it's also bad compared to chatgpt, or even bing.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
    • [โ€“] 1 point 3 years ago

    Im looking forward to foss ai solutions have their breakthrough, but for now, they cant compete with proprietary Software. Except maybe stable Diffusion

  • permalink
  • fedilink
  • source
    •
    [โ€“] 1 point 3 years ago

    Worth noting that if you want a local LLM on android MLCChat can run Vicuna-7B, RedPajama and several other models from huggingface on fairly average hardware. The interface is still basic but it's functional.

  • permalink
  • fedilink
  • source
    •