updated models3.json - Githubissues

nomic-ai / gpt4all

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

https://nomic.ai/gpt4all

MIT License

70.09k stars 7.66k forks source link

updated models3.json #2731

Closed 3Simplex closed 2 months ago

3Simplex commented 2 months ago

Describe your changes

Included llama 3.1 8b instruct

modified order for all models (MPT chat has two, needs attention.) set each parameter as needed.

Checklist before requesting a review

[x] I have performed a self-review of my code.
[ ] If it is a core feature, I have added thorough tests.
[ ] I have added thorough documentation for my code.
[ ] I have tagged PR with relevant project labels. I acknowledge that a PR without labels may be dismissed.
[ ] If this PR addresses a bug, I have provided both a screenshot/video of the original bug and the working solution.

Notes

Made small changes.

define the old llama 3 as 8b
Change Nous Hermes Mistral 7b DPO to "good" from best.
Suggest you look at MPT chat dual entries.

cebtenzzre commented 2 months ago

Suggest you look at MPT chat dual entries.

This was intentional - note the removedIn for the first model matching the requires entry for the second model (so they can have the same sort order, because only one ever shows up in the UI as currently implemented). The user is supposed to update the model between those GPT4All versions, as there was a breaking change to MPT in v2.7.3.