Was this model based of Mistral-7B-v0.2 from the start?
The recent changes to the README are a bit confusing. It used to say it was an imporved version of Mistral-7B-Instruct-v0.1, and based on Mistral-7B-v0.1. The weights haven't changed, but the base model is no longer the same as before?
Ai flux made a video about it
They probably just copied the README from the previous version and didn't properly update it until now.
They probably just copied the README from the previous version and didn't properly update it until now.
They only have like 5 models, I mean it’s not that hard to double check after months after the release.
I believe they didn’t want people to know there is a base v0.2 either for strategic reasons or just avoid people keep bugging them about using an instruct without having the pretrained model. (I am just happy we have a new open-source model, so thank you 🙏)
They probably just copied the README from the previous version and didn't properly update it until now.
They only have like 5 models, I mean it’s not that hard to double check after months after the release.
I believe they didn’t want people to know there is a base v0.2 either for strategic reasons or just avoid people keep bugging them about using an instruct without having the pretrained model. (I am just happy we have a new open-source model, so thank you 🙏)
Maybe, but since it came out all I've seen is people assuming it's a different base (and being sad that Mistral didn't release it's base alongside the Instruct version as they did with the v0.1 version) since it's config isn't using the same SWA window as mistralai/Mistral-7B-v0.1 or mistralai/Mistral-7B-Instruct-v0.1. Only recently with people posting about this README have I seen anything thinking otherwise.