Miscellaneous broken RSTs fixed (#16033)

Summary:
https://pytorch.org/docs/master/tensors.html#torch.Tensor.bernoulli_
https://pytorch.org/docs/master/torch.html#torch.addmm
https://pytorch.org/docs/master/distributed_deprecated.html#torch.distributed.deprecated.reduce_multigpu
Pull Request resolved: https://github.com/pytorch/pytorch/pull/16033

Differential Revision: D13671202

Pulled By: soumith

fbshipit-source-id: 276e10e610affe205376573e7f0f9894695d218d

diff --git a/torch/_tensor_docs.py b/torch/_tensor_docs.py
index bcc7d05..2e8e058 100644 (file)
--- a/torch/_tensor_docs.py
+++ b/torch/_tensor_docs.py
@@ -466,7 +466,7 @@ add_docstr_all('bernoulli_',
     The :math:`\text{i}^{th}` element of :attr:`self` tensor will be set to a
     value sampled from :math:`\text{Bernoulli}(\texttt{p\_tensor[i]})`.
 
-    :attr:`self` can have integral ``dtype``, but :attr`p_tensor` must have
+    :attr:`self` can have integral ``dtype``, but :attr:`p_tensor` must have
     floating point ``dtype``.
 
 See also :meth:`~Tensor.bernoulli` and :func:`torch.bernoulli`

diff --git a/torch/_torch_docs.py b/torch/_torch_docs.py
index 835958c..9178486 100644 (file)
--- a/torch/_torch_docs.py
+++ b/torch/_torch_docs.py
@@ -303,7 +303,7 @@ If :attr:`mat1` is a :math:`(n \times m)` tensor, :attr:`mat2` is a
 and :attr:`out` will be a :math:`(n \times p)` tensor.
 
 :attr:`alpha` and :attr:`beta` are scaling factors on matrix-vector product between
-:attr:`mat1` and :attr`mat2` and the added matrix :attr:`mat` respectively.
+:attr:`mat1` and :attr:`mat2` and the added matrix :attr:`mat` respectively.
 
 .. math::
     \text{out} = \beta\ \text{mat} + \alpha\ (\text{mat1}_i \mathbin{@} \text{mat2}_i)
@@ -604,7 +604,7 @@ in :attr:`input`.
 The returned :attr:`out` tensor only has values 0 or 1 and is of the same
 shape as :attr:`input`.
 
-:attr:`out` can have integral ``dtype``, but :attr`input` must have floating
+:attr:`out` can have integral ``dtype``, but :attr:`input` must have floating
 point ``dtype``.
 
 Args:

diff --git a/torch/distributed/deprecated/__init__.py b/torch/distributed/deprecated/__init__.py
index 151439a..f110775 100644 (file)
--- a/torch/distributed/deprecated/__init__.py
+++ b/torch/distributed/deprecated/__init__.py
@@ -337,7 +337,7 @@ def all_reduce(tensor, op=reduce_op.SUM, group=group.WORLD):
 
 def reduce_multigpu(tensor_list, dst, op=reduce_op.SUM, group=group.WORLD):
     r"""Reduces the tensor data on multiple GPUs across all machines. Each tensor
-    in :attr`tensor_list` should reside on a separate GPU.
+    in :attr:`tensor_list` should reside on a separate GPU.
 
     Only the GPU of ``tensor_list[0]`` on the process with rank :attr:`dst` is
     going to receive the final result.

diff --git a/torch/nn/modules/module.py b/torch/nn/modules/module.py
index 4de506d..e63222f 100644 (file)
--- a/torch/nn/modules/module.py
+++ b/torch/nn/modules/module.py
@@ -649,8 +649,8 @@ class Module(object):
         r"""Copies parameters and buffers from :attr:`state_dict` into only
         this module, but not its descendants. This is called on every submodule
         in :meth:`~torch.nn.Module.load_state_dict`. Metadata saved for this
-        module in input :attr:`state_dict` is provided as :attr`local_metadata`.
-        For state dicts without metadata, :attr`local_metadata` is empty.
+        module in input :attr:`state_dict` is provided as :attr:`local_metadata`.
+        For state dicts without metadata, :attr:`local_metadata` is empty.
         Subclasses can achieve class-specific backward compatible loading using
         the version number at `local_metadata.get("version", None)`.