|
--- |
|
language: es |
|
tags: |
|
- Spanish |
|
- BART |
|
- biology |
|
- medical |
|
- seq2seq |
|
license: mit |
|
thumbnail: https://huggingface.co/Narrativa/NarbioBART/resolve/main/NarbioBART-logo.png |
|
--- |
|
|
|
<div style="text-align:center;width:250px;height:250px;"> |
|
<img src="https://huggingface.co/Narrativa/NarbioBART/resolve/main/NarbioBART-logo.png" alt="NarbioBART logo""> |
|
</div> |
|
|
|
|
|
|
|
## 🦠 NarbioBART 🏥 |
|
|
|
**NarbioBART** (base) is a BART-like model trained on [Spanish Biomedical Crawled Corpus](https://zenodo.org/record/5510033#.Yhdk1ZHMLJx). |
|
|
|
BART is a transformer *encoder-decoder* (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function and (2) learning a model to reconstruct the original text. |
|
|
|
This model is particularly effective when fine-tuned for text generation tasks (e.g., summarization, translation) but also works well for comprehension tasks (e.g., text classification, question answering). |
|
|
|
|
|
|
|
## Training details |
|
|
|
- Dataset: `Spanish Biomedical Crawled Corpus` - 90% for training / 10% for validation. |
|
- Training script: see [here](https://github.com/huggingface/transformers/blob/main/examples/flax/language-modeling/run_bart_dlm_flax.py) |
|
|
|
|
|
## [Evaluation metrics](https://huggingface.co/mrm8488/bart-bio-base-es/tensorboard?params=scalars#frame) 🧾 |
|
|
|
|Metric | # Value | |
|
|-------|---------| |
|
|Accuracy| 0.802| |
|
|Loss| 1.04| |
|
|
|
|
|
## Benchmarks 🔨 |
|
|
|
WIP 🚧 |
|
|
|
## How to use with `transformers` |
|
|
|
```py |
|
from transformers import BartForConditionalGeneration, BartTokenizer |
|
|
|
model_id = "Narrativa/NarbioBART" |
|
|
|
model = BartForConditionalGeneration.from_pretrained(model_id, forced_bos_token_id=0) |
|
tokenizer = BartTokenizer.from_pretrained(model_id) |
|
|
|
def fill_mask_span(text): |
|
batch = tokenizer(text, return_tensors="pt") |
|
generated_ids = model.generate(batch["input_ids"]) |
|
print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True)) |
|
|
|
text = "your text with a <mask> token." |
|
fill_mask_span(text) |
|
``` |
|
|
|
## Citation |
|
|
|
``` |
|
@misc {narrativa_2023, |
|
author = { {Narrativa} }, |
|
title = { NarbioBART (Revision c9a4e07) }, |
|
year = 2023, |
|
url = { https://huggingface.co/Narrativa/NarbioBART }, |
|
doi = { 10.57967/hf/0500 }, |
|
publisher = { Hugging Face } |
|
} |
|
``` |
