提交 2e83c8bf 编写于 作者: A A. Unique TensorFlower

No public description

PiperOrigin-RevId: 555235095
上级 157d1ae2
......@@ -38,7 +38,7 @@ class OnDeviceEmbedding(tf.keras.layers.Layer):
is, not to scale). Setting this option to a float will let values in
output embeddings multiplied by scale_factor.
weight_fallback_dtype: When keras mix precision inferred wrong dtype for
varibales, `weight_fallback_dtype` will be used to define the dtype of
variables, `weight_fallback_dtype` will be used to define the dtype of
weights.
"""
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册