# IntelLabs/nlp-architect

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Repository: https://github.com/IntelLabs/nlp-architect
Canonical: https://ross.abutalabs.com/products/nlp-architect
Homepage: https://intellabs.github.io/nlp-architect
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deeplearning, nlp, nlu, tensorflow, dynet, deep-learning, pytorch, bert, transformers, quantization
Archived: true
Last push: 2022-11-07T16:21:47+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3030, "days_push": 1395, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2930, forks 440 (observed 2026-08-28T04:07:30.573409+00:00)

## What it is
NLP Architect is an open-source Python library from Intel AI Lab for exploring state-of-the-art deep learning topologies and optimization techniques for NLP and NLU neural networks. It provides core NLP models, novel NLU topologies, optimized models, and CLI/API tooling built on TensorFlow, PyTorch, and Dynet.

## Use cases
- train and run deep learning NLP models
- optimize NLP neural networks with quantization
- explore novel NLU model topologies
- use BERT and transformer models for NLP tasks
- run NLP model training and inference from the command line
- learn deep learning techniques for natural language processing

## When to choose
- you need a research-oriented NLP/NLU model library with optimization techniques like quantization
- you want to study Intel's NLP model implementations and topologies
- you're working with older TensorFlow/PyTorch/Dynet NLP stacks

## When to avoid
- you need a maintained library - Intel has discontinued it and it has known security escapes
- you need patches, bug fixes, or new releases - none are accepted anymore
- you want modern transformer tooling - use Hugging Face Transformers instead

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, nlp, machine-learning, cli
- domain: deep-learning, machine-learning
- platform: python, cross-platform
- tags: nlu, transformers, bert, quantization, model-optimization, tensorflow, pytorch, discontinued, natural-language-processing

## Member repositories
- IntelLabs/nlp-architect (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.573409+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:33:25.731199+00:00, confidence not recorded.
  - readme: https://github.com/IntelLabs/nlp-architect (fetched 2026-08-28T04:07:30.573409+00:00, sha a65d9890c7f3)
  - homepage: https://intellabs.github.io/nlp-architect (fetched 2026-08-29T09:48:42.817081+00:00, sha 9edb98ca38f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.