Models
MODELHugging Face
5/5

AfroLID v1.5

Malba Birifor(bfo)Classification (LID)SERENGETIXLMRobertaForSequenceClassification
View Source

Model Info

Language
Malba Birifor (bfo)
Architecture
XLMRobertaForSequenceClassification
Institution
Adebara, Elmadany, Abdul-Mageed, Inciarte (UBC-NLP)
Last Updated
14 May 2026

Intended Use Cases

LID for 517 African languages; macro-F1 97.41

License & Access

SPDX identifierApache-2.0

Open — attribution required; commercial use allowed.

Provenance

Fetch Timestamp
14 May 2026
Submitter
Adebara, Elmadany, Abdul-Mageed, Inciarte (UBC-NLP)

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 (17/18)

iso code
bfo
Model Name
AfroLID v1.5
Where is it hosted
HuggingFace/GitHub
Link
https://huggingface.co/UBC-NLP/afrolid_1.5
Year
2022
Creator/Author(s)
Adebara, Elmadany, Abdul-Mageed, Inciarte (UBC-NLP)
Paper Reference
AfroLID: A Neural Language Identification Tool for African Languages (EMNLP 2022); arXiv:2210.11744
NLP Task
Classification (LID)
Architecture
XLMRobertaForSequenceClassificationderivedHugging Face config: architectures / model_type
Base Model
SERENGETI
Fine-tuned?
Yes
License
Apache-2.0
Open Access
Open
Has Model Card
Yes
SOTA Tasks
LID for 517 African languages; macro-F1 97.41
Verified By
Not stated
Date Indexed
2026-05-14
Comment
Verified in supported-languages file

Readiness (LRS) (3/7)

model id
afrolid-v1-5-bfo
Model Type
Not stated
Training Data Sources
517 African languages multi-domain web corpus
Benchmark Used
Not stated
Benchmark Score
Not stated
Benchmark Date
Not stated
Status
Activederivedupdated within 3 years

Readiness Score Breakdown

5/5
Data Coverage69%
Model Availability100%
Benchmarks100%
Documentation93%
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.

Related Models