sophia-jax
PublicJAX implementation of 'Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training'
Creat:2024-05-23T23:14:09
Update:2024-11-07T07:05:54
2
Stars
0
Stars Increase
JAX implementation of 'Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training'