Merge pull request #2026 from mohantym:patch-1

PiperOrigin-RevId: 429476672

Author: copybara-github

site/en/tutorials/understanding/sngp.ipynb

@@ -74,7 +74,7 @@
         "\n",
         "This tutorial implements a deep residual network (ResNet)-based SNGP model on the [two moons](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_moons.html) dataset, and compares its uncertainty surface with that of two other popular uncertainty approaches - [Monte Carlo dropout](https://arxiv.org/abs/1506.02142) and [Deep ensemble](https://arxiv.org/abs/1612.01474)).\n",
         "\n",
-        "This tutorial illustrates the SNGP model on a toy 2D dataset. For an example of applying SNGP to a real-world natural language understanding task using  BERT-base, please see the [SNGP-BERT tutorial](https://www.tensorflow.org/official_models/tutorials/uncertainty_quantification_with_sngp_bert). For high-quality implementations of SNGP model (and many other uncertainty methods) on a wide variety of benchmark datasets (e.g., [CIFAR-100](https://www.tensorflow.org/datasets/catalog/cifar100), [ImageNet](https://www.tensorflow.org/datasets/catalog/imagenet2012), [Jigsaw toxicity detection](https://www.tensorflow.org/datasets/catalog/wikipedia_toxicity_subtypes), etc), please check out the [Uncertainty Baselines](https://github.com/google/uncertainty-baselines) benchmark."
+        "This tutorial illustrates the SNGP model on a toy 2D dataset. For an example of applying SNGP to a real-world natural language understanding task using  BERT-base, check out the [SNGP-BERT tutorial](https://www.tensorflow.org/text/tutorials/uncertainty_quantification_with_sngp_bert). For high-quality implementations of an SNGP model (and many other uncertainty methods) on a wide variety of benchmark datasets (such as [CIFAR-100](https://www.tensorflow.org/datasets/catalog/cifar100), [ImageNet](https://www.tensorflow.org/datasets/catalog/imagenet2012), [Jigsaw toxicity detection](https://www.tensorflow.org/datasets/catalog/wikipedia_toxicity_subtypes), etc), refer to the [Uncertainty Baselines](https://github.com/google/uncertainty-baselines) benchmark."
       ]
     },
     {