Upload 6 files

README.md

@@ -0,0 +1,21 @@
+---
+language: "en"
+license: apache-2.0
+tags:
+- token-classification
+- NER
+- Biomedical
+- Genetics
+datasets:
+- JNLPBA
+- BC2GM
+- tner/bc5cdr
+- jnlpba
+- bc2gm_corpus
+- drAbreu/bc4chemd_ner
+- linnaeus
+- ncbi_disease
+---
+BioBERT model fine-tuned in NER task with JNLPBA and BC2GM corpus for genetic class entities.
+
+This was fine-tuned in order to use it in a BioNER/BioNEN system which is available at: https://github.com/librairy/bio-ner

config.json

@@ -0,0 +1,34 @@
+{
+  "_num_labels": 3,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-GENETIC",
+    "1": "I-GENETIC",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-GENETIC": 0,
+    "I-GENETIC": 1,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bab85f4ea1e573a3299dd35f8bb13e48dc09e97f5e7899f59ccf2c0b9dac3c0
+size 430926282

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "init_inputs": [], "max_len": 512}