返回排行榜

turtlesoupy/this-word-does-not-exist

Pythonthisworddoesnotexist.com

This Word Does Not Exist

machine-learninggpt-2transformersnatural-language-processingnatural-language-understandingnatural-language-generation
Star 增长趋势
Star
1k
Forks
85
周增长
Issues
19
8001k
2020年5月2022年5月2024年6月2026年7月
制品库PyPIpip install this-word-does-not-exist
README

Word Does Not Exist Logo

This Word Does Not Exist

This is a project allows people to train a variant of GPT-2 that makes up words, definitions and examples from scratch.

For example

incromulentness (noun)

lack of sincerity or candor

"incromulentness in the manner of speech"

Check out https://www.thisworddoesnotexist.com as a demo

Check out https://twitter.com/robo_define for a twitter bot demo

Generating Words / Running Inference

Python deps are in https://github.com/turtlesoupy/this-word-does-not-exist/blob/master/cpu_deploy_environment.yml

Pre-trained model files:

To use them:

from title_maker_pro.word_generator import WordGenerator
word_generator = WordGenerator(
  device="cpu",
  forward_model_path="<somepath1>",
  inverse_model_path="<somepath2>",
  blacklist_path="<blacklist>",
  quantize=False,
)

# a word from scratch:
print(word_generator.generate_word())

# definition for a word you make up
print(word_generator.generate_definition("glooberyblipboop")) 

# new word made up from a definition
print(word_generator.generate_word_from_definition("a word that does not exist")) 

Training a model

For raw thoughts, take a look at some of the notebooks in https://github.com/turtlesoupy/this-word-does-not-exist/tree/master/notebooks

To train, you'll need to find a dictionary -- there is code to extract from

After extracting a dictionary you can use the master training script: https://github.com/turtlesoupy/this-word-does-not-exist/blob/master/title_maker_pro/train.py. A sample recent run is https://github.com/turtlesoupy/this-word-does-not-exist/blob/master/scripts/sample_run_parsed_dictionary.sh

Website Development Instructions

cd ./website
pip install -r requirements.txt
pip install aiohttp-devtools 
adev runserver
相关仓库
tensorflow/tensorflow

An Open Source Machine Learning Framework for Everyone

C++Apache License 2.0tensorflowmachine-learning
tensorflow.org
196.5k75.7k
f/prompts.chat

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

HTMLOtherchatgptai
prompts.chat
166.2k21.5k
huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

PythonPyPIApache License 2.0nlpnatural-language-processing
huggingface.co/transformers
162.8k34k
pytorch/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

PythonPyPIOtherneural-networkautograd
pytorch.org
101.8k28.4k
rasbt/LLMs-from-scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Jupyter NotebookOthergptlarge-language-models
amzn.to/4fqvn0D
99.5k15.3k
microsoft/ML-For-Beginners

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

Jupyter NotebookMIT Licensemldata-science
88.4k21.6k
Developer-Y/cs-video-courses

List of Computer Science courses with video lectures.

computer-sciencealgorithms
82.6k11.4k
mlabonne/llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Apache License 2.0coursellm
mlabonne.github.io/blog/
81.1k9.5k
netdata/netdata

The fastest path to AI-powered full stack observability, even for lean teams.

GoGo ModulesGNU General Public License v3.0monitoringdocker
netdata.cloud
79.8k6.5k
d2l-ai/d2l-zh

《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

PythonPyPIApache License 2.0deep-learningbook
zh.d2l.ai
79.1k12.3k
tesseract-ocr/tesseract

Tesseract Open Source OCR Engine (main repository)

C++Apache License 2.0tesseracttesseract-ocr
tesseract-ocr.github.io
75.5k10.7k
binhnguyennus/awesome-scalability

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

MIT Licensesystem-designbackend
72.6k7k