---
language: es
thumbnail: https://i.imgur.com/jgBdimh.png
license: apache-2.0
---
# BETO (Spanish BERT) + Spanish SQuAD2.0 + distillation using 'bert-base-multilingual-cased' as teacher
This model is a fine-tuned on [SQuAD-es-v2.0](https://github.com/ccasimiro88/TranslateAlignRetrieve) and **distilled** version of [BETO](https://github.com/dccuchile/beto) for **Q&A**.
Distillation makes the model **smaller, faster, cheaper and lighter** than [bert-base-spanish-wwm-cased-finetuned-spa-squad2-es](https://github.com/huggingface/transformers/blob/master/model_cards/mrm8488/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es/README.md)
This model was fine-tuned on the same dataset but using **distillation** during the process as mentioned above (and one more train epoch).
The **teacher model** for the distillation was `bert-base-multilingual-cased`. It is the same teacher used for `distilbert-base-multilingual-cased` AKA [**DistilmBERT**](https://github.com/huggingface/transformers/tree/master/examples/distillation) (on average is twice as fast as **mBERT-base**).
## Details of the downstream task (Q&A) - Dataset
[SQuAD-es-v2.0](https://github.com/ccasimiro88/TranslateAlignRetrieve)
| Dataset | # Q&A |
| ----------------------- | ----- |
| SQuAD2.0 Train | 130 K |
| SQuAD2.0-es-v2.0 | 111 K |
| SQuAD2.0 Dev | 12 K |
| SQuAD-es-v2.0-small Dev | 69 K |
## Model training
The model was trained on a Tesla P100 GPU and 25GB of RAM with the following command:
```bash
!export SQUAD_DIR=/path/to/squad-v2_spanish \
&& python transformers/examples/distillation/run_squad_w_distillation.py \
--model_type bert \
--model_name_or_path dccuchile/bert-base-spanish-wwm-cased \
--teacher_type bert \
--teacher_name_or_path bert-base-multilingual-cased \
--do_train \
--do_eval \
--do_lower_case \
--train_file $SQUAD_DIR/train-v2.json \
--predict_file $SQUAD_DIR/dev-v2.json \
--per_gpu_train_batch_size 12 \
--learning_rate 3e-5 \
--num_train_epochs 5.0 \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir /content/model_output \
--save_steps 5000 \
--threads 4 \
--version_2_with_negative
```
## Results:
TBA
### Model in action
Fast usage with **pipelines**:
```python
from transformers import *
# Important!: By now the QA pipeline is not compatible with fast tokenizer, but they are working on it. So that pass the object to the tokenizer {"use_fast": False} as in the following example:
nlp = pipeline(
'question-answering',
model='mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es',
tokenizer=(
'mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es',
{"use_fast": False}
)
)
nlp(
{
'question': '¿Para qué lenguaje está trabajando?',
'context': 'Manuel Romero está colaborando activamente con huggingface/transformers ' +
'para traer el poder de las últimas técnicas de procesamiento de lenguaje natural al idioma español'
}
)
# Output: {'answer': 'español', 'end': 169, 'score': 0.67530957344621, 'start': 163}
```
Play with this model and ```pipelines``` in a Colab:
1. Set the context and ask some questions:
2. Run predictions:
More about ``` Huggingface pipelines```? check this Colab out:
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488)
> Made with ♥ in Spain