Difference between revisions of "NaNoGenMo 2019 - GPT-2 Edition"

From ChipWiki
Jump to navigationJump to search
(Starting point)
 
(added gpt2, Parl.AI, textworld)
Line 1: Line 1:
 
[The Basics]
 
[The Basics]
 +
My goal this year was to take some random text, character, and location generators and build a basic recursive quest engine.
 +
 +
Let's unpack that.  All I want for now is:
 +
* locations - a small network of places, with the ability for characters to travel between them
 +
* characters - a recurring finite set of characters who travel between the locations and interact when they're in the same place
 +
** stretch goal - interact when they're passing one another!
 +
* recursive - the idea is that we have a world... it has, say, cities, within cities are places (inns, bars, markets), within those may be rooms... or maybe our recursion is deep enough at two levels
 +
 +
Eh, maybe that's even too much.  I work a super lot and in eight days of November so far all I've done is written those bullets.  But let's see what's out there...
 +
 +
[[[progress...]]]
 +
So there are some good generators out there that sort of start to do what I want.  I may just daisy chain them together... listed a few below.
 +
 +
 +
[Local laptop]
 +
 +
[[gpt-2]]
 
This: https://openai.com/blog/better-language-models/
 
This: https://openai.com/blog/better-language-models/
 
Made this: https://github.com/openai/gpt-2
 
Made this: https://github.com/openai/gpt-2
 +
Which made this: https://colab.research.google.com/drive/1gB03iSnshYcSzSCrS9gPGcoOFCpMhVq_
  
[Local laptop]
+
hit this bug: https://github.com/openai/gpt-2/issues/178
  
[[gpt-2]]
 
 
  <nowiki>
 
  <nowiki>
 
git clone https://github.com/openai/gpt-2.git && cd gpt-2
 
git clone https://github.com/openai/gpt-2.git && cd gpt-2
 
docker build --tag gpt-2 -f Dockerfile.cpu .
 
docker build --tag gpt-2 -f Dockerfile.cpu .
 +
</nowiki>
 +
 +
Need to run this on AWS or something:
 +
<nowiki>
 +
2019-11-09 20:43:18.919955: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
 +
2019-11-09 20:43:23.418088: W tensorflow/core/framework/allocator.cc:122] Allocation of 154389504 exceeds 10% of system memory.
 +
2019-11-09 20:43:23.722155: W tensorflow/core/framework/allocator.cc:122] Allocation of 154389504 exceeds 10% of system memory.
 +
2019-11-09 20:43:44.915623: W tensorflow/core/framework/allocator.cc:122] Allocation of 18137088 exceeds 10% of system memory.
 +
2019-11-09 20:43:45.006514: W tensorflow/core/framework/allocator.cc:122] Allocation of 18210816 exceeds 10% of system memory.
 +
2019-11-09 20:43:45.102333: W tensorflow/core/framework/allocator.cc:122] Allocation of 18284544 exceeds 10% of system memory.
 
</nowiki>
 
</nowiki>
  
Line 15: Line 42:
 
git clone https://github.com/facebookresearch/ParlAI.git
 
git clone https://github.com/facebookresearch/ParlAI.git
 
cd ParlAI; python setup.py develop
 
cd ParlAI; python setup.py develop
 +
</nowiki>
 +
 +
[[textworld]]
 +
From: https://www.microsoft.com/en-us/research/project/textworld/
 +
Yields: https://github.com/microsoft/textworld
 +
 +
hit this bug: https://github.com/authomatic/chromedriver_installer/issues/11
 +
<nowiki>
 +
pip install textworld
 
</nowiki>
 
</nowiki>

Revision as of 20:46, 9 November 2019

[The Basics] My goal this year was to take some random text, character, and location generators and build a basic recursive quest engine.

Let's unpack that. All I want for now is:

  • locations - a small network of places, with the ability for characters to travel between them
  • characters - a recurring finite set of characters who travel between the locations and interact when they're in the same place
    • stretch goal - interact when they're passing one another!
  • recursive - the idea is that we have a world... it has, say, cities, within cities are places (inns, bars, markets), within those may be rooms... or maybe our recursion is deep enough at two levels

Eh, maybe that's even too much. I work a super lot and in eight days of November so far all I've done is written those bullets. But let's see what's out there...

[[[progress...]]] So there are some good generators out there that sort of start to do what I want. I may just daisy chain them together... listed a few below.


[Local laptop]

gpt-2 This: https://openai.com/blog/better-language-models/ Made this: https://github.com/openai/gpt-2 Which made this: https://colab.research.google.com/drive/1gB03iSnshYcSzSCrS9gPGcoOFCpMhVq_

hit this bug: https://github.com/openai/gpt-2/issues/178

git clone https://github.com/openai/gpt-2.git && cd gpt-2
docker build --tag gpt-2 -f Dockerfile.cpu .

Need to run this on AWS or something:

2019-11-09 20:43:18.919955: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-11-09 20:43:23.418088: W tensorflow/core/framework/allocator.cc:122] Allocation of 154389504 exceeds 10% of system memory.
2019-11-09 20:43:23.722155: W tensorflow/core/framework/allocator.cc:122] Allocation of 154389504 exceeds 10% of system memory.
2019-11-09 20:43:44.915623: W tensorflow/core/framework/allocator.cc:122] Allocation of 18137088 exceeds 10% of system memory.
2019-11-09 20:43:45.006514: W tensorflow/core/framework/allocator.cc:122] Allocation of 18210816 exceeds 10% of system memory.
2019-11-09 20:43:45.102333: W tensorflow/core/framework/allocator.cc:122] Allocation of 18284544 exceeds 10% of system memory.

Parl.AI

git clone https://github.com/facebookresearch/ParlAI.git
cd ParlAI; python setup.py develop

textworld From: https://www.microsoft.com/en-us/research/project/textworld/ Yields: https://github.com/microsoft/textworld

hit this bug: https://github.com/authomatic/chromedriver_installer/issues/11

pip install textworld