* do initial run on full context
* decrement while loop iterations
* add context to output
* remove first param
* removing first param: change shape invariant
* models_dir argument to allow models in a separate folder
* default value for models_dir to be same as before
* allow environment variables and user home in models_dir
This write-up was loosely inspired in part by Mitchell et al.’s work on
[Model Cards for Model Reporting](https://arxiv.org/abs/1810.03993).
Adding such model usage sections could be good practice in general for
open source research projects with potentially broad applications.
added python download script and modified requirements to add the modules needed. Tested in Windows Version 10.0.17134 Build 17134 and Ubuntu 18.04.1 LTS
This PR adds better initial parameters to the conditional sample generation command in the docs.
The results are pretty poor in the interactive script with the default settings.
Now, you'll get better results if you run the interactive samples.
This fixes https://github.com/openai/gpt-2/issues/26
``` File "C:\Users\James Pollack\Desktop\gpt-2\src\encoder.py", line 112, in get_encoder
bpe_data = f.read()
File "C:\Anaconda\envs\gpt-2\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 66951: character maps to <undefined>```
