Update README.md

README.md

@@ -51,9 +51,16 @@ sample_outputs = model.generate(
     num_return_sequences=20
 )
 
-print("Output:\n" + 100 * '-')
+print("Output:\
+" + 100 * '-')
 for i, sample_output in enumerate(sample_outputs):
   m = tokenizer.decode(sample_output, skip_special_tokens=True)
   m = m.split("TODO")[1].strip()
   print("{}: TODO{}".format(i, m))
 ```
+
+
+## TODO
+
+- [ ] Preprocess the data in a better way
+- [ ] Download github and train it on everything