Models
MODELHugging Face
5/5

mmBERT-base Multilingual BERT (JHU-CLSP)

Dagbani(dag)LMBERT-basedModernBertForMaskedLM
View Source

Model Info

Language
Dagbani (dag)
Architecture
ModernBertForMaskedLM
Institution
JHU CLSP
Last Updated
27 Oct 2026

Intended Use Cases

Multilingual language modeling

License & Access

SPDX identifierMIT

Open — attribution required; commercial use allowed.

Provenance

Source URL
https://huggingface.co/jhu-clsp/mmBERT-base
Fetch Timestamp
27 Oct 2026
Submitter
JHU CLSP

Full Record

20 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (16/18)

iso code
dag
Model Name
mmBERT-base Multilingual BERT (JHU-CLSP)
Where is it hosted
HuggingFace
Link
https://huggingface.co/jhu-clsp/mmBERT-base
Year
2023
Creator/Author(s)
JHU CLSP
Paper Reference
https://arxiv.org/abs/2509.06888
NLP Task
LM
Architecture
ModernBertForMaskedLMderivedHugging Face config: architectures / model_type (replaces the library name 'transformers', kept in `library`)
Base Model
BERT-based
Fine-tuned?
Yes
License
MIT
Open Access
Open
Has Model Card
Yes
SOTA Tasks
Multilingual language modeling
Verified By
Not stated
Date Indexed
2026-10-27
Comment
Not stated

Readiness (LRS) (4/7)

model id
mmbert-base-multilingual-bert-jhu-clsp-dag
Model Type
LLM
Training Data Sources
Multilingual web text
Benchmark Used
Not stated
Benchmark Score
Not stated
Benchmark Date
Not stated
Status
Activederivedupdated within 3 years

Readiness Score Breakdown

5/5
Data Coverage100%
Model Availability100%
Benchmarks100%
Documentation73%
Recency100%

Representativeness

Gender Balance
Regional Distribution
Dialect Coverage
Inclusivity
Relations Explorer link

Also Available In

This is the same multilingual corpus, sliced for other languages the platform indexes it under.

model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAbé(aba)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAbidji(abi)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAbua(abn)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesKyode(acd)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAcholi(ach)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

jhu-clsp/mmBERT-base

Multilingual BERT-base model tagged for Dangme (ada) on HuggingFace. 313K downloads. Also available: jhu-clsp/mmBERT-small. Verify depth of Dangme coverage i…

507 languagesDangme(ada)BERTLM
HUHugging Face
Open11 May 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAdele(ade)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAdhola(adh)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAdjoukrou(adj)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesTunisian Arabic(aeb)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAfrikaans(afr)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAhanta(aha)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAdja(ajg)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesSiwu(akp)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAlur(alz)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesHamer(amf)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAmharic(amh)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAndoni(ann)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesDenya(anv)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026
model

mmBERT-base

fill-mask model · ModernBertForMaskedLM · jhu-clsp

507 languagesAnyin(any)ModernBertForMaskedLMfill-mask
HUHugging Face
Open27 Oct 2026

Related Models

model

GlotLID Language Identification Model (CIS-LMU)

Language Identification model · fasttext · CIS-LMU (LMU Munich)

550 languages2 copiesDagbani(dag)fastText-basedLanguage Identification
HUHugging Face
Open27 Oct 2026
model

Griot-Nano-1 Ghanaian Language ASR (Qlerqly)

ASR model · pytorch · Qlerqly

4 languagesDagbani(dag)Conformer CTC (153M)ASR
HUHugging Face
Restricted27 Oct 2026
model

XEUS Cross-lingual Speech Encoder

ASR model · espnet · ESPnet Team

1,424 languagesDagbani(dag)HuBERT-basedASR
HUHugging Face
Restricted27 Oct 2026