Doc styling (#8067)

* Important files

* Styling them all

* Revert "Styling them all"

This reverts commit 7d029395fdae8513b8281cbc2a6c239f8093503e.

* Syling them for realsies

* Fix syntax error

* Fix benchmark_utils

* More fixes

* Fix modeling auto and script

* Remove new line

* Fixes

* More fixes

* Fix more files

* Style

* Add FSMT

* More fixes

* More fixes

* More fixes

* More fixes

* Fixes

* More fixes

* More fixes

* Last fixes

* Make sphinx happy

src/transformers/modeling_flax_utils.py

@@ -35,7 +35,8 @@ logger = logging.get_logger(__name__)
 
 @jax.jit
 def gelu(x):
-    r"""Gaussian error linear unit activation function.
+    r"""
+    Gaussian error linear unit activation function.
 
     Computes the element-wise function:
 
@@ -43,9 +44,8 @@ def gelu(x):
       \mathrm{gelu}(x) = \frac{x}{2} \left(1 + \mathrm{tanh} \left(
         \sqrt{\frac{2}{\pi}} \left(x + 0.044715 x^3 \right) \right) \right)
 
-    We explicitly use the approximation rather than the exact formulation for
-    speed. For more information, see `Gaussian Error Linear Units (GELUs)
-    <https://arxiv.org/abs/1606.08415>`_, section 2.
+    We explicitly use the approximation rather than the exact formulation for speed. For more information, see
+    `Gaussian Error Linear Units (GELUs) <https://arxiv.org/abs/1606.08415>`_, section 2.
     """
     return x * 0.5 * (1.0 + jax.lax.erf(x / jnp.sqrt(2.0)))