# terrifyzhao/bert-utils

一行代码使用BERT生成句向量，BERT做文本分类、文本相似度计算

Repository: https://github.com/terrifyzhao/bert-utils
Canonical: https://ross.abutalabs.com/products/bert-utils
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2019-10-14T06:52:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2773, "days_push": 2515, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1668, forks 421 (observed 2026-08-28T04:05:19.813912+00:00)

## What it is
A Python library that simplifies Google's BERT to generate sentence vectors with one line of code and perform text classification and text similarity computation. It wraps pre-trained BERT models (e.g., Chinese BERT) with easy encode and train/eval/test APIs.

## Use cases
- generate sentence embeddings from bert
- compute text similarity between sentences
- fine-tune bert for text classification
- get sentence vectors in one line of python
- chinese text semantic matching
- encode sentences into fixed-size vectors

## When to choose
- you need a minimal wrapper around Google BERT for sentence vectors or classification
- you work with Chinese text and want to use the pre-trained Chinese BERT model
- you want simple train/eval/predict APIs for BERT-based classification

## When to avoid
- you need actively maintained code or recent TensorFlow compatibility
- you want multilingual or modern transformer models beyond original BERT
- you prefer PyTorch or Hugging Face Transformers ecosystem

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, nlp, llm-inference
- domain: machine-learning, deep-learning
- platform: python
- tags: bert, sentence-embeddings, text-classification, text-similarity, tensorflow, chinese-nlp, natural-language-processing

## Member repositories
- terrifyzhao/bert-utils (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:19.813912+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 2026-08-30T03:42:51.407178+00:00, confidence not recorded.
  - readme: https://github.com/terrifyzhao/bert-utils (fetched 2026-08-28T04:05:19.813912+00:00, sha 58fbf1b9acfb)
- Data as of 2026-08-30T08:39:29.467469+00:00.