Fix SM Model Internal Reproducibility Bug (#34)

* Fix SM Model reproducibility bug

vocab is in different order every time, causing unseen words to use
different random states

* Make requirements.txt usable from conda and pip

The existing torch requirement does not work with conda or pip.
Also upgrade pytorch version while we are at it.

sm_cnn/requirements.txt

@@ -2,4 +2,4 @@ gensim==1.0.1
 nltk==3.2.1
 numpy==1.11.3
 pandas==0.19.2
-torch==0.1.11+b13b701
+pytorch==0.1.12

sm_cnn/utils.py

@@ -155,7 +155,7 @@ def read_in_dataset(dataset_folder, set_folder, stop_punct=False, dash_split=Fal
     for sentence in all_data:
         for term in sentence.split():
             vocab_set.add(term)
-    vocab = list(vocab_set)
+    vocab = sorted(list(vocab_set))
 
     return [questions, sentences, labels, max(len_q_list), max(len_s_list), vocab]