[DOC] Add to the gallery an example on a small language model

This example demonstrates how to train a small-scale transformer-based language model (inspired by NanoGPT) on the Tiny Shakespeare dataset.  The core idea is to train a model that can predict the next character in a sequence of text based on the characters that came before it.

PiperOrigin-RevId: 611085293

docs/conf.py

@@ -227,6 +227,7 @@ def new_process_docstring(app, what, name, obj, options, lines):
 nb_execution_allow_errors = False
 nb_execution_excludepatterns = [
     # slow examples
+    'nanolm.ipynb',
     'cifar10_resnet.ipynb',
     'adversarial_training.ipynb',
     'reduce_on_plateau.ipynb',
@@ -296,6 +297,7 @@ def linkcode_resolve(domain, info):
 
 intersphinx_mapping = {
     'jax': ('https://jax.readthedocs.io/en/latest/', None),
+    'flax': ('https://flax.readthedocs.io/en/latest/', None),
 }
 
 source_suffix = ['.rst', '.md', '.ipynb']

docs/gallery.rst

@@ -150,6 +150,23 @@
       <div class="sphx-glr-thumbnail-title">Adversarial training of CNN on MNIST.</div>
     </div>
 
+
+.. raw:: html
+
+    <div class="sphx-glr-thumbcontainer" tooltip="Character-level Transformer on Tiny Shakespeare.">
+
+.. only:: html
+
+  .. image:: /images/examples/tiny_shakespeare.png
+     :alt: Character-level Transformer on Tiny Shakespeare
+
+  :doc:`_collections/examples/nanolm`
+
+.. raw:: html
+
+      <div class="sphx-glr-thumbnail-title">Character-level Transformer on Tiny Shakespeare.</div>
+    </div>
+
 .. raw:: html
 
     </div>