datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
gliner_review_comparisoneval-gliner2-fold3-20260708eval-gliner2-ner-fin-dice-soft-20260709eval-gliner2-ner-bionlp2004-boundary-smoothing-validationeval-gliner2-fold2-20260708eval-gliner2-ner-ontonotes5-boundary-smoothing-testeval-gliner2-ner-fin-boundary-smoothing-validationeval-gliner2-fold0-20260708eval-gliner2-ner-bionlp2004-boundary-smoothing-testeval-gliner2-ner-ncbi_disease-boundary-smoothing-validationeval-gliner2-ner-wnut2017-boundary-smoothing-testeval-gliner2-ner-conll2003-boundary-smoothing-testeval-gliner2-ner-fin-boundary-smoothing-testeval-gliner2-ner-bc5cdr-boundary-smoothing-validationeval-gliner2-pii-gretel-setgliner2-sentiment-luna-pilot-500
GLiNER2 Sentiment Luna Pilot 500
This dataset preserves the 500 records used in an enriched sentiment evaluation of two GLiNER2 models. It contains public user-generated social-media text and may include incidental personal information present in the original public comments. Use human review before operational or consequential use.
Important limitations
luna_sentiment is a synthetic reference produced by gpt-5.6-luna, not human annotation or ground truth.… See the full description on the dataset page: https://huggingface.co/datasets/erickdp/gliner2-sentiment-luna-pilot-500.eval-gliner2-ner-ontonotes5-boundary-smoothing-validationeval-gliner2-ner-fin-lossablation
fin — loss ablation (5 config x 3 seed)
base model: fastino/gliner2-multi-v1
dataset: quynong/fin (4 nhan), eval tren split test
train: 8 epochs, batch 16, early-stopping patience 2, seeds [42, 43, 44]
eval: --threshold 0.7 --use-desc --schema-case original --no-extra-val (giong nhau cho ca 5 config)
Ket qua (micro F1 %, mean +/- std tren seed)
mode
config
n seeds
micro F1
macro F1
micro P
micro R
lenient
bce
3
77.88 +/- 4.74
41.96 +/- 8.81
88.63… See the full description on the dataset page: https://huggingface.co/datasets/AITeamUIT/eval-gliner2-ner-fin-lossablation.eval-gliner2-ner-wnut2017-boundary-smoothing-validationeval-gliner2-fold0-20260811eval-gliner2-ner-mit_restaurant-boundary-smoothing-testeval-gliner2-ner-classweight-3seed
Class-weighted loss — 3 seed x 4 dataset
train: --loss-class-weight tren fastino/gliner2-multi-v1, batch 16, patience 2, seeds [42, 43, 44]
eval : --threshold 0.7 --use-desc --schema-case original --no-extra-val (giong loss ablation)
dataset
epochs
eval split
strict macro F1
lenient micro F1
conll2003
6
test
86.06 +/- 0.95
89.31 +/- 0.95
ontonotes5
3
test
77.47 +/- 0.51
90.30 +/- 0.06
fin
8
test
38.15 +/- 2.40
75.92 +/- 1.36
mit_restaurant
6
test
81.55 +/-… See the full description on the dataset page: https://huggingface.co/datasets/AITeamUIT/eval-gliner2-ner-classweight-3seed.eval-gliner2-ner-ontonotes5-affine-boundary-smoothing-testeval-gliner2-ner-mit_restaurant-affine-boundary-smoothing-validationeval-gliner2-fold1-20260708eval-gliner2-fold4-20260708eval-gliner2-ner-ncbi_disease-boundary-smoothing-testeval-gliner2-ner-mit_restaurant-boundary-smoothing-validationeval-gliner2-ner-bc5cdr-boundary-smoothing-testeval-gliner2-ner-conll2003-affine-validation
