gpt4all
gpt4all copied to clipboard
nomic-ai
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
### Feature Request Hi team, I’d like to ask whether it’s possible to use BGE-M3 as the text embedding model. After testing it, I found that BGE-M3 provides better context...
I INSTALLED IT IT SAID THAT MY CPU ISNT GOOD ENOUGH. THEN I TRIED TO UNINSTALL IT AND WONT UNINSTALL. WHAT THE HELL. THIS SHOULD WORK ON MY LAPTOP.
### Bug Report dell rtx5090 24G. 2T harddisk 32G memory I downloaded the latest GPT4All, installed some local offline large model(gguf llm), and started analyzing, embedding the slices of the...
Add the same setting as in ALpaca. When the setting is enabled, the time of the message request will be displayed in the chat. The time at which the message...
### Bug Report It is not possible to remove a LocalDocs collection while the indexing/embedding is running. If one added a large collection that would take a long time to...
Use Case: I have lots of GGUF models downloaded for use in LMStudio and other programs. I would like to have GPT4All access that folder rather than downloading the models...
> only _Originally posted by @sanch274F in [b666d16](https://github.com/nomic-ai/gpt4all/commit/b666d16db5aeab8b91aaf7963adcee9c643734d7#r165254576)_
Is it possible to compile it without having a GPU? I am on Debian 13 swaywm/wayland. If it is possible to compile then what are the steps?
