Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/lonepatient/torchblocks

A PyTorch-based toolkit for natural language processing
https://github.com/lonepatient/torchblocks

advertising bert multilabel-classification named-entity-recognition nlp pytorch relation-classification siamese-network text-classification text-similarity transformers triplet-loss

Last synced: 7 days ago
JSON representation

A PyTorch-based toolkit for natural language processing

Host: GitHub
URL: https://github.com/lonepatient/torchblocks
Owner: lonePatient
License: mit
Created: 2020-06-21T15:09:07.000Z (over 4 years ago)
Default Branch: master
Last Pushed: 2023-03-10T02:28:39.000Z (over 1 year ago)
Last Synced: 2024-11-01T08:17:06.763Z (12 days ago)
Topics: advertising, bert, multilabel-classification, named-entity-recognition, nlp, pytorch, relation-classification, siamese-network, text-classification, text-similarity, transformers, triplet-loss
Language: Python
Homepage:
Size: 481 KB
Stars: 153
Watchers: 7
Forks: 25
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        ## TorchBlocks

(Work in Progress!!)

A PyTorch-based toolkit for natural language processing

![python](https://img.shields.io/badge/-Python_3.7_%7C_3.8_%7C_3.9_%7C_3.10-blue?logo=python&logoColor=white)

![pytorch](https://img.shields.io/badge/PyTorch_1.10+-ee4c2c?logo=pytorch&logoColor=white)

![black](https://img.shields.io/badge/Code%20Style-Black-black.svg?labelColor=gray)

![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)

### Requirements

- torch>=1.10.0

- tokenizers >= 0.7.0

- transformers>=4.10.0

- torchmetrics>=0.11.3

TorchBlocks requires Python 3.7+. We recommend installing TorchBlocks in a Linux or OSX environment.

### Installation

Recommended (because of active development):

```shell

git clone https://github.com/lonePatient/TorchBlocks.git

cd TorchBlocks

python setup.py install

```

⚠️**Note:** This project is still in the development stage and some of the interfaces are subject to change.

### Tutorials

* Tutorial 1 (text classification): [task_text_classification_cola.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_text_classification_cola.py)

* Tutorial 2 (siamese similarity): [task_siamese_similarity_afqmc.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_siamese_similarity_afqmc.py)

* Tutorial 3 (sequence labeling): [task_sequence_labeling_ner_crf.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_sequence_labeling_ner_crf.py)

* Tutorial 4 (sentence similarity): [task_sentence_similarity_lcqmc.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_sentence_similarity_lcqmc.py)

* Tutorial 5 (triple similarity): [task_triple_similarity_epidemic.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_triple_similarity_epidemic.py)

* Tutorial 6 (sequence labeling): [task_sequence_labeling_resume_beam_search_softmax.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_sequence_labeling_resume_beam_search_softmax.py)

* Tutorual 7 (sequence labeling): [task_sequence_labeling_resume_global_pointer.py](https://github.com/lonePatient/TorchBlocks/blob/master/examples/task_sequence_labeling_resume_global_pointer.py)

* Example scripts for each task: [TorchBlocks/examples/](https://github.com/lonePatient/TorchBlocks/tree/master/examples)