Downloads · 30 days
77
44% of all-time downloads
STRIDE-lab/biolinkbert-number-of-participants-20250221
biolinkbert-number-of-participants-20250221 is a text classification model from STRIDE-lab. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
Fine-tuned model from the PsyNamic project.
Downloads · 30 days
77
44% of all-time downloads
All-time downloads
177
Public
Parameters
108M
433 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors433 MB · 100%
From the Hugging Face model README
Fine-tuned model from the PsyNamic project.
Superseded. This is the model of the initial PsyNamic submission (tag
submission-v1). It was replaced after retraining under a corrected protocol (Nov 2026) by STRIDE-lab/biomedbert-abstract-number-of-participants-20261106. All current models: PsyNamic collection.
michiyasunaga/BioLinkBERT-base
Number of Participants
Categorizes studies by the total number of participants included.
| ID | Label | Definition |
|---|---|---|
| 0 | 1-20 | – |
| 1 | 100-199 | – |
| 2 | 200-499 | – |
| 3 | 21-40 | – |
| 4 | 41-60 | – |
| 5 | 500-999 | – |
| 6 | 61-80 | – |
| 7 | 81-100 | – |
| 8 | Not applicable | E.g., for most systematic reviews. |
| 9 | Unknown | – |
| 10 | ≥1000 | – |
{
"mode": "train",
"data": "<private_dataset>",
"task": "Number of Participants",
"model": "biolinkbert",
"cross_val": false,
"batch_size": 8,
"learning_rate": 5e-05,
"weight_decay": 0.01,
"lr_scheduler": "linear",
"warmup_ratio": 0.1,
"epochs": 30,
"dropout": 0.1,
"early_stopping_patience": 5,
"gradient_clipping": 0.1,
"device": "cuda",
"load": null,
"max_length": 512,
"is_multilabel": false
}