Uploaded the model

README.md

@@ -1,3 +1,15 @@
 ---
 license: cc-by-sa-4.0
 ---
+
+# est-roberta-hist-ner
+
+## Model description 
+
+est-roberta-hist-ner is an [Est-RoBERTa](https://huggingface.co/EMBEDDIA/est-roberta) based model fine-tuned for named entity recognition in Estonian 19th century parish court records (for details, see [this repository](https://github.com/soras/vk_ner_lrec_2022)). 
+The following types of entities are recognized: person names (PER), ambiguous locations-organizations (LOC_ORG), locations (LOC), organizations (ORG) and MISC (miscellaneous names).
+
+## How to use 
+
+Recommended usage of the model is with approriate pre- and postprocessing by EstNLTK. 
+For an usage example, see this tutorial: [https://github.com/soras/vk\_ner\_lrec\_2022/blob/main/using\_bert\_ner\_tagger.ipynb](https://github.com/soras/vk_ner_lrec_2022/blob/main/using_bert_ner_tagger.ipynb) 

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "est-roberta",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-LOC_ORG",
+    "2": "B-MISC",
+    "3": "B-ORG",
+    "4": "B-PER",
+    "5": "I-LOC",
+    "6": "I-LOC_ORG",
+    "7": "I-MISC",
+    "8": "I-ORG",
+    "9": "I-PER",
+    "10": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-LOC_ORG": 1,
+    "B-MISC": 2,
+    "B-ORG": 3,
+    "B-PER": 4,
+    "I-LOC": 5,
+    "I-LOC_ORG": 6,
+    "I-MISC": 7,
+    "I-ORG": 8,
+    "I-PER": 9,
+    "O": 10
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4b9dfc103efe51bc82e21cf0424f613b9e7ec571975cb9929c4dc85730bc61
+size 464825015

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4efafd8f3bf5547faaa9561ce37181ee61b2aada8bdcee7ad5f2aac10a1a76
+size 935725

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "do_lower_case": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "est-roberta"}