Skip to main content

BentoML artifact framework for Q&A Transformers

Project description

qandaxfmrartifact

BentoML artifact framework for Q&A Transformers.

Installation:

pip install qandaxfmrartifact==0.0.1

Usage example (decorate service):

from qandaxfmrartifact.QandaTransformersModelArtifact import QandaTransformersModelArtifact

@artifacts([QandaTransformersModelArtifact('albert')])
class MyBentoService(BentoService):

Usage example (package model):

svc = MyBentoService()

opts = {
    'embedder_model_path': my_embedder_model_path,
}

svc.pack('albert', my_transformer_model_path, opts)

Alternatively, during training:

svc.pack('albert', {'model': my_trained_model, 'tokenizer': my_tokenizer, 'embedder': my_embedder})

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

qandaxfmrartifact-0.0.10.tar.gz (3.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

qandaxfmrartifact-0.0.10-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file qandaxfmrartifact-0.0.10.tar.gz.

File metadata

  • Download URL: qandaxfmrartifact-0.0.10.tar.gz
  • Upload date:
  • Size: 3.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.54.0 CPython/3.8.5

File hashes

Hashes for qandaxfmrartifact-0.0.10.tar.gz
Algorithm Hash digest
SHA256 e4b1a62080ede5bc041e77326fbb26442d201c22507189d04957c6c42ce39c7b
MD5 e9d1d4aa71bdee0941017d8aa80d2a36
BLAKE2b-256 4e0ef1b1c81463b49be43f0f67011aa683876fc8ac525c7fccc7ed889b32699c

See more details on using hashes here.

File details

Details for the file qandaxfmrartifact-0.0.10-py3-none-any.whl.

File metadata

  • Download URL: qandaxfmrartifact-0.0.10-py3-none-any.whl
  • Upload date:
  • Size: 4.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.54.0 CPython/3.8.5

File hashes

Hashes for qandaxfmrartifact-0.0.10-py3-none-any.whl
Algorithm Hash digest
SHA256 3fd5f4130d910a749ab421c8512a5da968c6888d79d969bad8f1a629a5aa6230
MD5 b1045a96dac58e8df665e102bbd82b00
BLAKE2b-256 6b1b4bf1c178b860395128b696ffb89466d545f7b381d4caa850a5a680b792d2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page