Join the community of Machine Learners and AI enthusiasts.
Sign Up
mamba is now available in transformers. Thanks to
@tridao
and
@albertgu
for this brilliant model! 🚀 and the amazing mamba-ssm kernels powering this!Could you share the conversion script?
The weights are compatible out of the box, you just need to correctly set the config !
Hi, great work! i wonder is it possible to train mamba from scratch using transformers and not only fine tune if from pretrained model? If so would you mind sharing some sample code? I want to test this model with different number of parameters.
