TicTacToe GPT Finetuning
========================
Simple python implementation of Tic Tac Toe.
Designed to make GPT able to recognize valid moves in Tic Tac Toe
::
$ pip install tictactoe-gpt-finetuning
Examples
--------
Generate a game:
.. code:: python
from tictactoe_gpt_finetuning import tictactoe
print( tictactoe.generate_random_game() )
Generate many games:
.. code:: python
from tictactoe_gpt_finetuning import tictactoe
print( tictactoe.generate_n_games() )
Initialize and use the game board to place in top left:
.. code:: python
from tictactoe_gpt_finetuning import tictactoe
b = tictactoe.BoardState()
b.make_move( 0, 0, 'x' )
print( b )
# output:
# x - -
# - - -
# - - -
Train a Model
-------------
We can compare inputs to outputs of the model, and compare
predictions of the model before and after finetuning.
.. code:: python
from tictactoe import Model, finetune, compare_tictactoe_predictions
gpt = Model()
# See what predictions look like before finetuning
compare_tictactoe_predictions( gpt )
# Fine-tune the model
finetune( gpt, n_epochs=10 )
# See what new predictions look like after finetuning
compare_tictactoe_predictions
Raw data
{
"_id": null,
"home_page": "https://github.com/pesvut/tictactoe-gpt-finetuning",
"name": "tictactoe-gpt-finetuning",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "tictactoe,llm,language-models",
"author": "Nicky Pochinkov",
"author_email": "work@nicky.pro",
"download_url": "https://files.pythonhosted.org/packages/f6/8f/1e64cdedf60ffef82158c690e1725b2f43746d6d305f398aca7309e07a2e/tictactoe-gpt-finetuning-0.1.3.tar.gz",
"platform": null,
"description": "TicTacToe GPT Finetuning\n========================\n\nSimple python implementation of Tic Tac Toe.\n\nDesigned to make GPT able to recognize valid moves in Tic Tac Toe\n\n::\n\n $ pip install tictactoe-gpt-finetuning\n\nExamples\n--------\n\nGenerate a game:\n\n.. code:: python\n\n from tictactoe_gpt_finetuning import tictactoe\n print( tictactoe.generate_random_game() )\n\nGenerate many games:\n\n.. code:: python\n\n from tictactoe_gpt_finetuning import tictactoe\n print( tictactoe.generate_n_games() )\n\nInitialize and use the game board to place in top left:\n\n.. code:: python\n\n from tictactoe_gpt_finetuning import tictactoe\n b = tictactoe.BoardState()\n b.make_move( 0, 0, 'x' )\n print( b )\n # output:\n # x - -\n # - - -\n # - - -\n\nTrain a Model\n-------------\n\nWe can compare inputs to outputs of the model, and compare\npredictions of the model before and after finetuning.\n\n.. code:: python\n\n from tictactoe import Model, finetune, compare_tictactoe_predictions\n gpt = Model()\n\n # See what predictions look like before finetuning\n compare_tictactoe_predictions( gpt )\n\n # Fine-tune the model\n finetune( gpt, n_epochs=10 )\n\n # See what new predictions look like after finetuning\n compare_tictactoe_predictions\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Python tic tac toe state generator and GPT fine tuning",
"version": "0.1.3",
"split_keywords": [
"tictactoe",
"llm",
"language-models"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f68f1e64cdedf60ffef82158c690e1725b2f43746d6d305f398aca7309e07a2e",
"md5": "55c57ce1a4b533e881458f067c6c9abb",
"sha256": "f376d792a80aa0e322fbc2d9e08c7ebda83e87c29d6f3d30d63aef5dcccbca5d"
},
"downloads": -1,
"filename": "tictactoe-gpt-finetuning-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "55c57ce1a4b533e881458f067c6c9abb",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 5230,
"upload_time": "2023-01-16T23:08:55",
"upload_time_iso_8601": "2023-01-16T23:08:55.208333Z",
"url": "https://files.pythonhosted.org/packages/f6/8f/1e64cdedf60ffef82158c690e1725b2f43746d6d305f398aca7309e07a2e/tictactoe-gpt-finetuning-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-16 23:08:55",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "pesvut",
"github_project": "tictactoe-gpt-finetuning",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "tictactoe-gpt-finetuning"
}
JSON
