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/situqingyun/torchblocks-chen.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-1.0.1.10.tar.gz
(94.2 kB
view hashes)
Built Distribution
Close
Hashes for torchblocks_chen-1.0.1.10.tar.gz
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | bb55f922065fbf522d8e2c59b9b4ddb7b46fbbbea2aeeee2409425b8338bde98 |
|
| MD5 | d2ba2e42b20f12ad87adb310f902fde4 |
|
| BLAKE2b-256 | 490a5065964a1cc74d75f6fb19d210ba3c2b708646169819d33a9b7f503ab8ec |
Close
Hashes for torchblocks_chen-1.0.1.10-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 8531b6c3c2387aba835168ee112a7257d6da86ed5f7a165ed00a7d8db3edda75 |
|
| MD5 | f30019f1c6defbcaf6ca94c591027a39 |
|
| BLAKE2b-256 | a559d0949bc581154e23bff2da37f0e2ddefa5a5c9ec974a2f489907ccd058d0 |
