From b650dc95df8b9754693b83e9c004395e2e2888ad Mon Sep 17 00:00:00 2001
From: ale <ale@debian>
Date: Fri, 30 Jul 2021 17:40:31 +0200
Subject: [PATCH] initial commit

---
 README.md          | 36 ++++++++++++++++++++++++++++++++++++
 docker-compose.yml | 15 +++++++++++++++
 maria/Dockerfile   | 11 +++++++++++
 maria/roberta.py   | 12 ++++++++++++
 4 files changed, 74 insertions(+)
 create mode 100644 README.md
 create mode 100644 docker-compose.yml
 create mode 100644 maria/Dockerfile
 create mode 100644 maria/roberta.py

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..5a2599b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,36 @@
+# MarIA la Biblioteca Nacional y el BSC crean un sistema especializado en el idioma español para mejorar las respuestas de las IA en nuestra lengua
+
+[https://www.xataka.com/robotica-e-ia/maria-biblioteca-nacional-bsc-crean-sistema-especializado-idioma-espanol-para-mejorar-respuestas-ia-nuestra-lengua](https://www.xataka.com/robotica-e-ia/maria-biblioteca-nacional-bsc-crean-sistema-especializado-idioma-espanol-para-mejorar-respuestas-ia-nuestra-lengua)
+
+[https://github.com/PlanTL-SANIDAD/lm-spanish](https://github.com/PlanTL-SANIDAD/lm-spanish)
+
+[https://huggingface.co/BSC-TeMU/roberta-large-bne](https://huggingface.co/BSC-TeMU/roberta-large-bne)
+
+```
+$ python3 roberta.py "la inteligencia <mask> es el presente"
+[' emocional', ' humana', ' no', ' artificial', ' colectiva']
+
+$ python3 roberta.py "la curiosidad <mask> al gato"
+[' mueve', ' mató', ' mata', ' ayuda', ' atrae']
+```
+
+## Build
+
+```
+docker-compose build
+
+or
+
+docker build -t maria ./maria
+```
+
+## Run
+
+```
+$ docker run --name maria --rm maria "hola <mask>, ¿qué tal?"
+[' guapa', ' chicas', ' amigos', ' chicos', ' amigo']
+```
+
+## License
+
+MIT
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..1ff7fe2
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,15 @@
+version: '2'
+
+services:
+    maria:
+        build: ./maria
+        image: maria
+        hostname: maria
+        container_name: maria
+        restart: always
+        networks:
+            net:
+
+networks:
+  net:
+
diff --git a/maria/Dockerfile b/maria/Dockerfile
new file mode 100644
index 0000000..fbd6019
--- /dev/null
+++ b/maria/Dockerfile
@@ -0,0 +1,11 @@
+FROM python:3
+RUN curl https://sh.rustup.rs -sSf | sh -s -- -y
+RUN . /root/.cargo/env && pip3 install transformers torch flask
+RUN mkdir -p /maria
+WORKDIR /maria
+RUN git clone https://huggingface.co/BSC-TeMU/roberta-base-bne
+COPY ./roberta.py /maria/roberta.py
+RUN python3 roberta.py "hola <mask>"
+CMD "hola <mask>"
+ENTRYPOINT ["python3", "roberta.py"]
+
diff --git a/maria/roberta.py b/maria/roberta.py
new file mode 100644
index 0000000..f542dc9
--- /dev/null
+++ b/maria/roberta.py
@@ -0,0 +1,12 @@
+from transformers import AutoModelForMaskedLM
+from transformers import AutoTokenizer, FillMaskPipeline
+from pprint import pprint
+import sys
+tokenizer_hf = AutoTokenizer.from_pretrained('BSC-TeMU/roberta-base-bne')
+model = AutoModelForMaskedLM.from_pretrained('BSC-TeMU/roberta-base-bne')
+model.eval()
+pipeline = FillMaskPipeline(model, tokenizer_hf)
+text = sys.argv[1:]
+res_hf = pipeline(text)
+pprint([r['token_str'] for r in res_hf])
+