BeardedMonster/afriberta-large-masakhapos-multilingual

afriberta-large fine-tuned on masakhapos (multilingual)

Fine-tuned from castorini/afriberta_large on masakhapos, multilingual protocol, over 20 language(s): bam, bbj, ewe, fon, hau, ibo, kin, lug, luo, mos, nya, pcm, sna, swa, tsn, twi, wol, xho, yor, zul

setting	value
epochs	50
learning rate	5e-05
batch size	32
max length	256
metric	accuracy
mean score	0.8771

Per-language scores are in metrics.json.

Loading

from transformers import AutoTokenizer, AutoModelForTokenClassification
tok = AutoTokenizer.from_pretrained("BeardedMonster/afriberta-large-masakhapos-multilingual")
model = AutoModelForTokenClassification.from_pretrained("BeardedMonster/afriberta-large-masakhapos-multilingual")

id2label is set, so predictions decode straight to tag names.

Provenance and limits

Produced by this project's benchmark harness, which reproduces the published MasakhaNER 2.0 baselines to within ~0.25 F1, so these numbers are calibrated rather than ad hoc. Scores come from a single run; the baseline papers average over 5, so treat small differences as noise.

The base model's own licence and terms govern any derivative use — check castorini/afriberta_large before relying on this checkpoint.