Jared Nielsen
2020-02-14 07:21
Kinda hacky方式：
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients([
(grad, var)
for (grad, var) in zip(gradients, model.trainable_variables)
if grad is not None
])
热门帖子
相关问题
热门github
1
2
3
5
6
7
8
11
13
14
15
Mamba is a new state space model architecture showing promising performance on information-dense data such as language modeling, where previous subquadratic models fall short of Transformers. It is based on the line of progress on structured state space models, with an efficient hardware-aware design and implementation in the spirit of FlashAttention.
(翻译：Mamba 是一种新的状态空间模型架构，在信息密集型数据（例如语言建模）上显示出良好的性能，而之前的二次模型在 Transformers 方面存在不足。它基于结构化状态空间模型的进展，并本着FlashAttention的精神进行高效的硬件感知设计和实现。)