👨🏻⚕️ Spanish Clinical Encoders Analysis
Collection
Models and datasets used in the paper `A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks` • 91 items • Updated • 3
Token Classification
Transformers
PyTorch
Safetensors
Spanish
deberta-v2
text-classification
biomedical
clinical
spanish
mdeberta-v3-base
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("IIC/mdeberta-v3-base-nubes")
model = AutoModelForSequenceClassification.from_pretrained("IIC/mdeberta-v3-base-nubes")Quick Links
mdeberta-v3-base-nubes
This model is a finetuned version of mdeberta-v3-base for the nubes dataset used in a benchmark in the paper TODO. The model has a F1 of 0.919
Please refer to the original publication for more information TODO LINK
Parameters used
| parameter | Value |
|---|---|
| batch size | 32 |
| learning rate | 3e-05 |
| classifier dropout | 0 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
BibTeX entry and citation info
TODO
- Downloads last month
- 6
Collection including IIC/mdeberta-v3-base-nubes
Evaluation results
- f1 on nubestest set self-reported0.919
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="IIC/mdeberta-v3-base-nubes")