Fixed the bug in the TensorFlow git URL. (#726)

Issue #725

doc/sphinx/source/framework-integration-guides.rst

@@ -218,8 +218,8 @@ Build with an XLA plugin to ``libngraph``
 
    .. code-block:: console
 
-      $ git clone git@github.com:NervanaSystems/ngraph-tensorflow.git
-      $ cd ngraph-tensorflow
+      $ git clone git@github.com:NervanaSystems/ngraph-tensorflow-1.3.git
+      $ cd ngraph-tensorflow-1.3
 
 #. Now run :command:`configure` and choose `y` when prompted to build TensorFlow
    with XLA just-in-time compiler.
@@ -299,4 +299,4 @@ your cloned version of `ngraph-tensorflow`_:
 .. _ngraph-neon repo's README: https://github.com/NervanaSystems/ngraph-neon/blob/master/README.md
 .. _neon docs: https://github.com/NervanaSystems/neon/tree/master/doc
 .. _being the fastest: https://github.com/soumith/convnet-benchmarks/
-.. _for training CNN-based models with GPUs: https://www.microway.com/hpc-tech-tips/deep-learning-frameworks-survey-tensorflow-torch-theano-caffe-neon-ibm-machine-learning-stack/
\ No newline at end of file
+.. _for training CNN-based models with GPUs: https://www.microway.com/hpc-tech-tips/deep-learning-frameworks-survey-tensorflow-torch-theano-caffe-neon-ibm-machine-learning-stack/