A PyTorch-based toolkit for natural language processing
Project description
TorchBlocks
A PyTorch-based toolkit for natural language processing
Requirements
- transformers>=4.1.1
- torch>=1.6.0
TorchBlocks requires Python 3.6+. We recommend installing TorchBlocks in a Linux or OSX environment.
Installation
Recommended (because of active development):
git clone https://github.com/lonePatient/TorchBlocks.git
cd TorchBlocks
python setup.py install
Tutorials
- Tutorial 1 (text classification): task_text_classification_cola.py
- Tutorial 2 (siamese similarity): task_siamese_similarity_afqmc.py
- Tutorial 3 (sequence labeling): task_sequence_labeling_ner_crf.py
- Tutorial 4 (sentence similarity): task_sentence_similarity_lcqmc.py
- Tutorial 5 (triple similarity): task_triple_similarity_epidemic.py
- Example scripts for each task: TorchBlocks/examples/
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torchblocks_chen-1.0.1.tar.gz
(84.3 kB
view details)
Built Distribution
File details
Details for the file torchblocks_chen-1.0.1.tar.gz.
File metadata
- Download URL: torchblocks_chen-1.0.1.tar.gz
- Upload date:
- Size: 84.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.1.2.post20210112 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | f0c5c18b9fd4383f53cce246b04a0ca4161196d78599736b7958e71ead0a67e3 |
|
| MD5 | 4a2a69cae99ce2f6f3561789f67c891a |
|
| BLAKE2b-256 | f688f571f7d48ad530e4174cc1719aaf13520fdf8844e280d94d84c862c87c8f |
File details
Details for the file torchblocks_chen-1.0.1-py3-none-any.whl.
File metadata
- Download URL: torchblocks_chen-1.0.1-py3-none-any.whl
- Upload date:
- Size: 123.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.1.2.post20210112 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 0c91f6f725b18c08d2da3202edd466182a7b21d1bcce42f09b6241c21014a76a |
|
| MD5 | f32723e3e729d35c8579cf87d40fcd3f |
|
| BLAKE2b-256 | ae7b27036637d26d672b0f72755b192297c01d8363c8d4a32c7a284b226244cc |
