# appvision-ai/fast-bert

Super easy library for BERT based NLP models

Repository: https://github.com/appvision-ai/fast-bert
Canonical: https://ross.abutalabs.com/products/fast-bert
Language: Python
License: Apache-2.0
License Family: permissive
Topics: bert, fast-bert, fastai, transformers
Last push: 2024-08-19T09:41:38+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2694, "days_push": 744, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1917, forks 339 (observed 2026-08-28T04:05:53.833641+00:00)

## What it is
Fast-Bert is a Python deep learning library for training and deploying BERT, RoBERTa, and XLNet based models for NLP tasks, starting with multi-class and multi-label text classification. It wraps the Hugging Face PyTorch BERT library with a fast.ai-inspired API, including a learning rate finder, LAMB optimizer support, and AWS Sagemaker deployment.

## Use cases
- fine-tune bert for text classification on my own dataset
- train a multi-label text classifier with transformers
- compare bert xlnet roberta for classification
- find the best learning rate for transformer fine-tuning
- deploy a bert model to aws sagemaker for inference
- train distilbert classifier with minimal code

## When to choose
- you want a simple high-level API for BERT-style text classification
- you need multi-class or multi-label classification with BERT, RoBERTa, or XLNet
- you want built-in learning rate finding and LAMB optimizer support
- you plan to deploy trained models on AWS Sagemaker

## When to avoid
- you need NLU tasks beyond text classification like NER or question answering
- you want the latest transformer features and broad model support (prefer Hugging Face Transformers)
- you need actively developed features or support for recent Python versions
- you are not working in PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, llm-training
- domain: machine-learning, deep-learning
- platform: python
- tags: bert, xlnet, roberta, text-classification, transformers, fastai, fine-tuning, pytorch, sagemaker, natural-language-processing

## Member repositories
- appvision-ai/fast-bert (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:53.833641+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 2026-08-30T03:10:08.530594+00:00, confidence not recorded.
  - readme: https://github.com/appvision-ai/fast-bert (fetched 2026-08-28T04:05:53.833641+00:00, sha 72bd5b34b0bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.