Generative Pretrained Transformer 2 (GPT-2) for Language Modeling using the PyTorch-Transformers library.
Project description
Next Word Prediction
Generative Pretrained Transformer 2 (GPT-2) for Language Modeling using the PyTorch-Transformers library.
Installation
Requires python>=3.5, pytorch>=1.6.0, pytorch-transformers>=1.2.0
pip install next-word-prediction
How to use
>>> from next_word_prediction import GPT2
>>> gpt2 = GPT2()
>>> text = "The course starts next"
>>> gpt2.predict_next(text, 5)
The course starts next ['week', 'to', 'month', 'year', 'Monday']
Demo via Streamlit
streamlit run app/run.py
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file next_word_prediction-0.2.0.tar.gz.
File metadata
- Download URL: next_word_prediction-0.2.0.tar.gz
- Upload date:
- Size: 2.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
14f2bed9244f64107b982d4ee437d65c926fe5616dbb04bec97f52b1fe57d009
|
|
| MD5 |
faab683433aaa34a52464eec3f839143
|
|
| BLAKE2b-256 |
5d4e9886136a81a58faa583323aa18a50d6a375d71e3a118cc1f56e1d42bdc1d
|
File details
Details for the file next_word_prediction-0.2.0-py3-none-any.whl.
File metadata
- Download URL: next_word_prediction-0.2.0-py3-none-any.whl
- Upload date:
- Size: 3.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
82fbd5afb016d8bb5683c6fc1a2884542792a5bad8dea46cb13a684e962e3b7c
|
|
| MD5 |
444389a8b709c28561418511845484ec
|
|
| BLAKE2b-256 |
2e4b859c502c14f4e5377183ab072a2a80deee1a91a68e27f6d843429da4b084
|