Initial commit

README.md

@@ -0,0 +1,44 @@
+---
+language:
+- es
+license: apache-2.0
+tags:
+- "national library of spain"
+- "spanish"
+- "bne"
+- "capitel"
+- "ner"
+datasets:
+- "bne"
+- "capitel"  
+metrics:
+- "f1"
+
+---
+
+# Spanish RoBERTa-base trained on BNE finetuned for CAPITEL Named Entity Recognition (NER) dataset.
+RoBERTa-base-bne is a transformer-based masked language model for the Spanish language. It is based on the [RoBERTa](https://arxiv.org/abs/1907.11692) base model and has been pre-trained using the largest Spanish corpus known to date, with a total of 570GB of clean and deduplicated text processed for this work, compiled from the web crawlings performed by the  [National Library of Spain (Biblioteca Nacional de España)](http://www.bne.es/en/Inicio/index.html) from 2009 to 2019.
+
+Original pre-trained model can be found here: https://huggingface.co/BSC-TeMU/roberta-base-bne
+
+## Dataset
+The dataset used is the one from the [CAPITEL competition at IberLEF 2020](https://sites.google.com/view/capitel2020) (sub-task 1).
+
+## Evaluation and results
+F1 Score: 0.8959
+
+For evaluation details visit our [GitHub repository](https://github.com/PlanTL-SANIDAD/lm-spanish).
+
+
+## Citing 
+Check out our paper for all the details: https://arxiv.org/abs/2107.07253
+```
+@misc{gutierrezfandino2021spanish,
+      title={Spanish Language Models}, 
+      author={Asier Gutiérrez-Fandiño and Jordi Armengol-Estapé and Marc Pàmies and Joan Llop-Palao and Joaquín Silveira-Ocampo and Casimiro Pio Carrino and Aitor Gonzalez-Agirre and Carme Armentano-Oller and Carlos Rodriguez-Penagos and Marta Villegas},
+      year={2021},
+      eprint={2107.07253},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "../models/bne-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": { 
+    "0": "B_OTH",
+    "1": "I_OTH",
+    "2": "E_OTH",
+    "3": "S_ORG",
+    "4": "S_OTH",
+    "5": "B_PER",
+    "6": "E_PER",
+    "7": "B_ORG",
+    "8": "E_ORG",
+    "9": "S_LOC",
+    "10": "S_PER",
+    "11": "B_LOC",
+    "12": "E_LOC",
+    "13": "I_PER",
+    "14": "I_ORG",
+    "15": "I_LOC",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B_OTH": 0,
+    "I_OTH": 1,
+    "E_OTH": 2,
+    "S_ORG": 3,
+    "S_OTH": 4,
+    "B_PER": 5,
+    "E_PER": 6,
+    "B_ORG": 7,
+    "E_ORG": 8,
+    "S_LOC": 9,
+    "S_PER": 10,
+    "B_LOC": 11,
+    "E_LOC": 12,
+    "I_PER": 13,
+    "I_ORG": 14,
+    "I_LOC": 15,
+    "O": 16
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3793b143635ec31d9848367e697c0a6965f56eb4b3ce7872612986a8851ad67
+size 496347953

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "../models/bne-base"}