Skip to main content

Transformers based NLP models

Project description

PyPI - Package Version MIT License PyPI pyversions Python package Dependency Review

NLP Models

A repository for building transformer based nlp models

Run Llama2 on consumer CPU

Run Chat UI on CPU

cd pipelines/nlp_models/
streamlit run app.py

Run Chat cmd line on CPU

llm_app chat -s 'hi there'

Models

  1. bert_classifier A wrapper package around BERT-based classification models

  2. multi_task_model An implementation of multi-tasking model built on encoder models

  3. GPT-2

  1. Falcon 7B
  1. Quantized Llama2 models

Installation

Install from PyPi

pip install nlp-models

Install from source

git clone git@github.com:minggnim/nlp-models.git
pip install -r requirements

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

nlp-models-4.1.0.tar.gz (15.5 kB view details)

Uploaded Source

Built Distribution

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

nlp_models-4.1.0-py3-none-any.whl (19.1 kB view details)

Uploaded Python 3

File details

Details for the file nlp-models-4.1.0.tar.gz.

File metadata

  • Download URL: nlp-models-4.1.0.tar.gz
  • Upload date:
  • Size: 15.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for nlp-models-4.1.0.tar.gz
Algorithm Hash digest
SHA256 d2227ac947cebb35871a62f7ee39f27545fa52bc244b27d1e991e77e7caa71d1
MD5 e09f9a73a3ede16e119c83dc9d3c056d
BLAKE2b-256 3be2e7c1e1c444aa71525befa927bba204524c1e22a164ae9be3310ca6086287

See more details on using hashes here.

File details

Details for the file nlp_models-4.1.0-py3-none-any.whl.

File metadata

  • Download URL: nlp_models-4.1.0-py3-none-any.whl
  • Upload date:
  • Size: 19.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.17

File hashes

Hashes for nlp_models-4.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6c4e08866f56b2d0f6d90693be92194c1f631060cc43b644e7297642229c4198
MD5 bbc51fe4139f8fa73c9a4a1b356b4fba
BLAKE2b-256 975b2c399e432d7d1bd3aee3798a1f46cb6b7403d9c7be8b5ee64dc741b5e131

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