PsyNamic
Collection
Biomedical BERT classification & NER for psychedelic therapy abstracts, powering https://psynamic.dcr.unibe.ch • 20 items • Updated
How to use STRIDE-lab/pubmedbert-condition-20250221 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="STRIDE-lab/pubmedbert-condition-20250221") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("STRIDE-lab/pubmedbert-condition-20250221")
model = AutoModelForSequenceClassification.from_pretrained("STRIDE-lab/pubmedbert-condition-20250221")Fine-tuned model from the PsyNamic project.
microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
Condition
{
"mode": "train",
"data": "<private_dataset>",
"task": "Condition",
"model": "pubmedbert",
"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": true
}