Upload config

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "michiyasunaga/BioLinkBERT-large",
+  "architectures": [
+    "BioNextTaggerModel"
+  ],
+  "args_random_seed": 42,
+  "attention_probs_dropout_prob": 0.1,
+  "augmentation": "unk",
+  "auto_map": {
+    "AutoConfig": "configuration_bionexttager.BioNextTaggerConfig"
+  },
+  "classifier_dropout": null,
+  "context_size": 2,
+  "crf_reduction": "mean",
+  "freeze": false,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-GeneOrGeneProduct",
+    "2": "I-GeneOrGeneProduct",
+    "3": "B-DiseaseOrPhenotypicFeature",
+    "4": "I-DiseaseOrPhenotypicFeature",
+    "5": "B-ChemicalEntity",
+    "6": "I-ChemicalEntity",
+    "7": "B-SequenceVariant",
+    "8": "I-SequenceVariant",
+    "9": "B-OrganismTaxon",
+    "10": "I-OrganismTaxon",
+    "11": "B-CellLine",
+    "12": "I-CellLine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-CellLine": 11,
+    "B-ChemicalEntity": 5,
+    "B-DiseaseOrPhenotypicFeature": 3,
+    "B-GeneOrGeneProduct": 1,
+    "B-OrganismTaxon": 9,
+    "B-SequenceVariant": 7,
+    "I-CellLine": 12,
+    "I-ChemicalEntity": 6,
+    "I-DiseaseOrPhenotypicFeature": 4,
+    "I-GeneOrGeneProduct": 2,
+    "I-OrganismTaxon": 10,
+    "I-SequenceVariant": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "crf-tagger",
+  "model_type_arch": "dense",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "p_augmentation": 0.5,
+  "pad_token_id": 0,
+  "percentage_tags": 0.75,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

configuration_bionexttager.py

@@ -0,0 +1,32 @@
+
+from transformers import PretrainedConfig, AutoConfig
+from typing import List
+
+
+class BioNextTaggerConfig(PretrainedConfig):
+    model_type = "crf-tagger"
+
+    def __init__(
+        self,
+        augmentation = "unk",
+        context_size = 64,
+        percentage_tags = 0.2,
+        p_augmentation = 0.5,
+        crf_reduction = "mean",
+        **kwargs,
+    ):
+        self.augmentation = augmentation
+        self.context_size = context_size
+        self.percentage_tags = percentage_tags
+        self.p_augmentation = p_augmentation
+        self.crf_reduction = crf_reduction
+        super().__init__(**kwargs)
+        
+    def get_backbonemodel_config(self):
+        backbonemodel_cfg = AutoConfig.from_pretrained(self._name_or_path)#.to_dict()
+        for k in backbonemodel_cfg.to_dict():
+            if hasattr(self, k):
+                setattr(backbonemodel_cfg,k, getattr(self,k))
+                
+        return backbonemodel_cfg
+