Closed SamKG closed 5 days ago
Hello,
I am wondering if there are any examples which use Flax (or just pure Jax) for mixture of experts models. I'd be happy to contribute one myself if there aren't any - just wondering if anyone has done the heavy lifting already.
found one here: https://github.com/google/flax/discussions/4035
Hello,
I am wondering if there are any examples which use Flax (or just pure Jax) for mixture of experts models. I'd be happy to contribute one myself if there aren't any - just wondering if anyone has done the heavy lifting already.