NERDA-Con

Extending NERDA Library for Continual Learning

Installation Guide

pip install NERDA-Con

Implementation and Execution

Training

model.train_next_task(training,validation)

The training and validation must be NERDA-optimized dataloaders.

Evaluation

model.evaluate_performance(test)

Shared Model

To set shared model parameters,

model.shared_model = model.transformer_model

NERDA

Nerda is a framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks.

@inproceedings{nerda,
  title = {NERDA},
  author = {Kjeldgaard, Lars and Nielsen, Lukas},
  year = {2021},
  publisher = {{GitHub}},
  url = {https://github.com/ebanalyse/NERDA}
}

Cite This Work

@inproceedings{nerda-con,
  title = {NERDA-Con},
  author = {Supriti Vijay, Aman Priyanshu},
  year = {2022},
  publisher = {{GitHub}},
  url = {https://github.com/SupritiVijay/NERDA-Con}
}

Metadata

Release files for NERDA-Con 0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for NERDA-Con 0.0
File	Size	Uploaded	Provenance	Actions
NERDA_Con-0.0.tar.gz	164.4 kB	May 3, 2022	Without provenance	Details for NERDA_Con-0.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for NERDA-Con 0.0
File	Interpreter	ABI	Platform	Actions Reset
NERDA_Con-0.0-py3-none-any.whl 21.3 kB May 3, 2022 Without provenance	Python 3	none	any	Details for NERDA_Con-0.0-py3-none-any.whl

Total release size: 185.7 kB

Release files / NERDA_Con-0.0.tar.gz

Download URL	NERDA_Con-0.0.tar.gz
Size	164.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`76820fd4c68fe3e1b6ebfd77ef529881c1e95cbb349dca77053204b160a693c0`
BLAKE2b-256 checksum How to use checksums	`3463470ceaf78839743330e4b69f2d73a5cfa3e91f9e7372e8d9274d076998da`
Upload date	May 3, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.8.0 pkginfo/1.8.2 readme-renderer/32.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.42.1 importlib-metadata/4.11.1 keyring/21.1.0 rfc3986/2.0.0 colorama/0.4.3 CPython/3.7.6`

Release files / NERDA_Con-0.0-py3-none-any.whl

Download URL	NERDA_Con-0.0-py3-none-any.whl
Size	21.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`fe4d2d960ccfc5ba3dd36a6489a5908fed8cacb9869d381b9b54dc9736ac39c6`
BLAKE2b-256 checksum How to use checksums	`b4c1e6e3a5c241a8657b8a404ed5552c81f41621f87afe8e9eb5400f2e766108`
Upload date	May 3, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.8.0 pkginfo/1.8.2 readme-renderer/32.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.42.1 importlib-metadata/4.11.1 keyring/21.1.0 rfc3986/2.0.0 colorama/0.4.3 CPython/3.7.6`

Security for NERDA-Con 0.0

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0 This release

May 3, 2022 2 release files No provenance

NERDA-Con 0.0