google-research/bert
TensorFlow code and pre-trained models for BERT observed · 2026-10-15
Health v2 · maintenance only
10/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases archived
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2917
- days_rel: n/a
- days_push: 819
- n_releases_24m: 0
Adoption not part of the score
40038 stars · 9659 forks observed · 2026-10-15
What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.98
Google's BERT repository provides TensorFlow implementations and pre‑trained checkpoints of the Bidirectional Encoder Representations from Transformers model. It includes a range of model sizes for flexible use in downstream NLP tasks.
Use cases
- fine‑tune BERT for question answering
- apply BERT to sentiment analysis
- use BERT for text classification
- perform named entity recognition with BERT
- run language inference (e.g., MNLI) using BERT
- extractive QA or passage ranking with BERT
- paraphrase detection and semantic similarity
When to choose
- You need state‑of‑the‑art transfer learning for English NLP tasks.
- You want a well‑maintained, widely‑cited model with many pre‑trained checkpoints.
- You have access to TensorFlow and can benefit from the smaller BERT variants for limited compute.
When to avoid
- You require ultra‑low latency inference on edge devices without GPU support.
- Your target language is not covered by the provided English‑only checkpoints.
- You prefer a non‑Transformer architecture or a library tied to a different framework (e.g., PyTorch).
Facets
library · maturity active
machine-learning nlp deep-learning artificial-intelligence deep-learning python windows bert pretrained-models language-model transformer tf2 text-embeddings natural-language-processing tensorflow linux macos
6 sources
- readme: https://github.com/google-research/bert · fetched 2026-10-15 · 9f0784648b42
- homepage: https://arxiv.org/abs/1810.04805 · fetched 2026-09-14 · cd9c49f5e17f
- site_page: https://info.arxiv.org/about/ourmembers.html · fetched 2026-09-14 · 10aa574961b4
- site_page: https://info.arxiv.org/about/donate.html · fetched 2026-09-14 · cca9c3a11c56
- site_page: https://info.arxiv.org/about · fetched 2026-09-14 · a1f16f915a9a
- site_page: https://info.arxiv.org/labs/index.html · fetched 2026-09-14 · b14a8d05a0ec
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| google-research/bert | main | 10 |
For agents
markdown · JSON · MCP: product_card(name="google-research/bert")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem