- cross-posted to:
- chatgpt@lemmy.world
- cross-posted to:
- chatgpt@lemmy.world
Meta has released llama 3.1. It seems to be a significant improvement to an already quite good model. It is now multilingual, has a 128k context window, has some sort of tool chaining support and, overall, performs better on benchmarks than its predecessor.
With this new version, they also released their 405B parameter version, along with the updated 70B and 8B versions.
I’ve been using the 3.0 version and was already satisfied, so I’m excited to try this.
the code is FOSS, the weights aren’t, this is pretty common with e.g. FOSS games, the only difference here is weights are much costlier to remake from scratch than game assets
The license has limitations and isn’t something standard like Apache
True, but it hardly matters for the source since the architecture is pulled into open source projects like transformers (Apache) and llama.cpp (MIT). The weights remain under the dubious Llama Community License, so I would only call the data “available” instead of “open”.
I’ll just stick to Mistral
Are you using mistral 7B?
I also really like that model and their fine-tunes. If licensing is a concern, it’s definitely a great choice.
Mistral also has a new model, Mistral Nemo. I haven’t tried it myself, but I heard it’s quite good. It’s also licensed under Apache 2.0 as far as I know.
Is it part of ollama?
Edit: https://ollama.com/library/mistral-nemo
Yes, you can find it here.