# google-bert/bert-base-multilingual-uncased

This model is an uncased multilingual BERT base model pretrained on the 102 languages with the largest Wikipedias using masked language modeling and next sentence prediction. It is intended mainly for fine tuning on downstream tasks such as sequence classification, token classification, and question answering, and it can be used directly for masked language modeling.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-google-bert-bert-base-multilingual-uncased
- Citation: google-bert/bert-base-multilingual-uncased. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-google-bert-bert-base-multilingual-uncased (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: fill-mask
- Framework: transformers
- License: apache-2.0: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/google-bert/bert-base-multilingual-uncased
- Hosting: hosted (9 files)
- Files: 9 hosted of 10 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 9 hosted of 10 listed
- Full repo upstream: 3.02 GB
- Recommended file: 672.2 MB · model.safetensors
- Download: https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/download-plan)
- Per-file SHA-256: available for 9 of 9 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 4086862
- Stars: 177
- Card completeness: 92%

## Description

This model is an uncased multilingual BERT base model pretrained on the 102 languages with the largest Wikipedias using masked language modeling and next sentence prediction. It is intended mainly for fine tuning on downstream tasks such as sequence classification, token classification, and question answering, and it can be used directly for masked language modeling.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: fill-mask
- Library: transformers
- Task categories: fill-mask
- Languages: multilingual, af, sq, ar, an, hy, ast, az
- Referenced datasets: wikipedia
- Paper ids: 1810.04805
- File hints: 10 upstream file samples

## Referenced Data

- Dataset: wikipedia
- Paper: 1810.04805

## File Hints

- .gitattributes
- README.md
- config.json
- flax_model.msgpack
- model.safetensors
- pytorch_model.bin
- tf_model.h5
- tokenizer.json
- tokenizer_config.json
- vocab.txt

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-07-29T22:21:43.809Z.
- Open license detected as apache-2.0.
- Model card references dataset context: wikipedia.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-google-bert-bert-base-multilingual-uncased
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-google-bert-bert-base-multilingual-uncased
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-google-bert-bert-base-multilingual-uncased&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-google-bert-bert-base-multilingual-uncased/decentralized-fallbacks