Initial commit

README.md

@@ -1,6 +1,6 @@
 ---
 language: es
-license: gpl-3.0
+license: gpl
 tags:
 - PyTorch
 - Transformers
@@ -36,12 +36,6 @@ for ent in ner_pipe(example):
     print(ent)
 ```
 
-```
-{'entity_group': 'LOC', 'score': 0.99795026, 'word': ' Sigüeiro', 'start': 22, 'end': 30}
-{'entity_group': 'LOC', 'score': 0.997823, 'word': ' Camino de Santiago', 'start': 38, 'end': 56}
-{'entity_group': 'ORG', 'score': 0.98481846, 'word': ' Ministerio de Industria y Competitividad', 'start': 85, 'end': 125}
-```
-
 ## Model performance
 
 entity|precision|recall|f1
@@ -50,9 +44,7 @@ PER|0.965|0.924|0.944
 ORG|0.900|0.701|0.788
 LOC|0.982|0.985|0.983
 MISC|0.798|0.874|0.834
-micro avg|0.964|0.968|0.966
-macro avg|0.911|0.871|0.887
-weighted avg|0.965|0.968|0.966
+Overall|0.964|0.968|0.966
 
 ## Training procedure
 

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-MISC",
+    "2": "B-ORG",
+    "3": "B-PER",
+    "4": "I-LOC",
+    "5": "I-MISC",
+    "6": "I-ORG",
+    "7": "I-PER",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-MISC": 1,
+    "B-ORG": 2,
+    "B-PER": 3,
+    "I-LOC": 4,
+    "I-MISC": 5,
+    "I-ORG": 6,
+    "I-PER": 7,
+    "O": 8
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "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 sha256:54853750d9a7acb21f7ab654bfdbed2a01f46f209e9d1aaf9502cf1952e8c4ed
+size 496311341

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 512,
+  "name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1283c01fe20d44d8f566f373f9c0086927abb23b9c7e7c7f8d3a5c64e28dff
+size 3515