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
Built Distributions
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 torchblocks-1.0.0.tar.gz.
File metadata
- Download URL: torchblocks-1.0.0.tar.gz
- Upload date:
- Size: 81.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
92c4f299b37e198396ed0bee87f38a0278f83d858a2e8529c60b2fa2975298c4
|
|
| MD5 |
9956761246f03f7dcba7f21a0527ebc0
|
|
| BLAKE2b-256 |
a8ea04f771f80dfb93be6de072dcfc0ab642efb14095c93963c437aed3c0d6af
|
File details
Details for the file torchblocks-1.0.0-py3.7.egg.
File metadata
- Download URL: torchblocks-1.0.0-py3.7.egg
- Upload date:
- Size: 286.0 kB
- Tags: Egg
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9faf2fe3664a11613151ca076b5e9a0c6fc2e0103b771086eb2dbbd85ad46e46
|
|
| MD5 |
2b77ddf09ef5a7603ffdb3236b034b3a
|
|
| BLAKE2b-256 |
bf0be36f830b25538f023e39043606ba637f8e0a4e9e071b67eb21401376689a
|
File details
Details for the file torchblocks-1.0.0-py3-none-any.whl.
File metadata
- Download URL: torchblocks-1.0.0-py3-none-any.whl
- Upload date:
- Size: 120.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4a0575d17196f66d79ad9830c626d5f47ca878eb88d19ef0e5cf2884150e1c32
|
|
| MD5 |
ffc3921fa78126c8bde6699d649fc8a0
|
|
| BLAKE2b-256 |
411ccf410629fa59b6389ea430c9e5db7432b28b7746bc2d2c546fa0259f5a78
|
