Fix broken links after we moved projects.

PiperOrigin-RevId: 416450920

official/README.md

@@ -58,12 +58,12 @@ In the near future, we will add:
 
 | Model | Reference (Paper) |
 |-------|-------------------|
-| [ALBERT (A Lite BERT)](nlp/albert) | [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942) |
-| [BERT (Bidirectional Encoder Representations from Transformers)](nlp/bert) | [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) |
+| [ALBERT (A Lite BERT)](nlp/MODEL_GARDEN.md#available-model-configs) | [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942) |
+| [BERT (Bidirectional Encoder Representations from Transformers)](nlp/MODEL_GARDEN.md#available-model-configs) | [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) |
 | [NHNet (News Headline generation model)](projects/nhnet) | [Generating Representative Headlines for News Stories](https://arxiv.org/abs/2001.09386) |
 | [Transformer](nlp/transformer) | [Attention Is All You Need](https://arxiv.org/abs/1706.03762) |
 | [XLNet](nlp/xlnet) | [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://arxiv.org/abs/1906.08237) |
-| [MobileBERT](nlp/projects/mobilebert) | [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://arxiv.org/abs/2004.02984) |
+| [MobileBERT](projects/mobilebert) | [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://arxiv.org/abs/2004.02984) |
 
 ### Recommendation
 

official/nlp/README.md

@@ -32,10 +32,10 @@ We provide SoTA model implementations, pre-trained models, training and
 evaluation examples, and command lines. Detail instructions can be found in the
 READMEs for specific papers.
 
-1.  [BERT](bert): [BERT: Pre-training of Deep Bidirectional Transformers for
+1.  [BERT](MODEL_GARDEN.md#available-model-configs): [BERT: Pre-training of Deep Bidirectional Transformers for
     Language Understanding](https://arxiv.org/abs/1810.04805) by Devlin et al.,
     2018
-2.  [ALBERT](albert):
+2.  [ALBERT](MODEL_GARDEN.md#available-model-configs):
     [A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942)
     by Lan et al., 2019
 3.  [XLNet](xlnet):