Spanish biomedical specialization
The model card describes a RoBERTa-based model trained on Spanish biomedical corpora assembled from public sources and crawlers.
Open Source Model Profile · PlanTL-GOB-ES
roberta-base-biomedical-es
roberta-base-biomedical-es is a PlanTL-GOB-ES RoBERTa fill-mask model for Spanish biomedical text. Its card documents downstream NER fine-tuning use.
- Publisher
- PlanTL-GOB-ES
- Task
- fill-mask
- Model type
- roberta
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
roberta-base-biomedical-es is published by PlanTL-GOB-ES as a fill-mask model for Spanish biomedical text. The captured configuration identifies RobertaForMaskedLM with model type roberta. According to the model card, it is a RoBERTa-based model trained on a Spanish biomedical corpus and directly usable for masked language modeling.
Recorded capabilities
Fill-mask plus downstream fine-tuning
According to the model card, the model is directly usable for fill-mask work and is intended for fine-tuning on Named Entity Recognition or Text Classification.
Documented V100 pretraining run
The card reports 48 hours on 16 NVIDIA V100 16GB GPUs with Adam, peak learning rate 0.0005, and a 2,048-sentence effective batch size.
Publisher-reported NER comparisons
According to the model card, the model scored 89.48 on PharmaCoNER, 83.87 on CANTEMIST, and 88.12 on ICTUSnet against mBERT and BETO baselines.
Use cases in the source record
- Spanish biomedical fill-mask prediction in the style of the card's clinical fill-mask examples.
- Fine-tuning for Spanish biomedical Named Entity Recognition or Text Classification, following the card's reported PharmaCoNER, CANTEMIST, and ICTUSnet comparisons.
Limitations and unknowns
- No parameter count was extracted from this record.
- Provider state is historical snapshot data and should be refreshed before being presented as current availability.
- Pretraining and benchmark figures come from the publisher model card and have not been independently verified by Ethen.
Source and provenance
Source: PlanTL-GOB-ES/roberta-base-biomedical-es
Captured: Unknown. Processed: 2026-09-07T19:34:35.677330+00:00.
Biomedical language model for Spanish Table of contents Click to expand Model description Intended uses and limitations How to use Limitations and bias Training Tokenization and model pretraining Training corpora and preprocessing Evaluation Additional information Author Contact information Copyright Licensing information Funding Disclaimer Model description Biomedical pretrained language model for Spanish. For more details about the corpus, the pretraining and the evaluation, check the official repository and read our preprint . Intended uses and limitations The model is ready-to-use only for masked language modelling to perform th…
F001F002F003F004F005F006F007F008F009F010F014F015F020F021F022F025