Add link to Github repository
#4
by
nielsr
HF staff
- opened
This PR adds a link to the Github repository for the Samba model, as mentioned in the paper. This makes it easier for users to access the training code.
Thank you for submitting the pull request.
We apologize for any confusion caused by the inaccurate README. The PLaMo 2 architecture is not exactly the same as Samba.
Here are the reasons for the differences:
- We needed normalization similar to Jamba to enhance training stability.
- We adopted the Mamba2 kernel to improve computation speed.
We have updated the README to include this information.