adding core files for protein structure model v2.1

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-chemical",
+    "2": "B-species",
+    "3": "B-gene",
+    "4": "I-gene",
+    "5": "B-taxonomy_domain",
+    "6": "I-chemical",
+    "7": "B-protein_type",
+    "8": "B-experimental_method",
+    "9": "I-experimental_method",
+    "10": "I-protein_type",
+    "11": "I-species",
+    "12": "B-evidence",
+    "13": "I-evidence",
+    "14": "B-protein",
+    "15": "I-protein",
+    "16": "B-protein_state",
+    "17": "B-site",
+    "18": "I-site",
+    "19": "B-structure_element",
+    "20": "I-structure_element",
+    "21": "B-complex_assembly",
+    "22": "I-protein_state",
+    "23": "I-complex_assembly",
+    "24": "B-ptm",
+    "25": "B-mutant",
+    "26": "I-mutant",
+    "27": "B-oligomeric_state",
+    "28": "B-residue_name_number",
+    "29": "B-bond_interaction",
+    "30": "I-bond_interaction",
+    "31": "B-residue_range",
+    "32": "I-residue_range",
+    "33": "B-residue_name",
+    "34": "B-residue_number",
+    "35": "I-ptm",
+    "36": "I-taxonomy_domain",
+    "37": "I-oligomeric_state",
+    "38": "I-residue_name_number",
+    "39": "I-residue_name",
+    "40": "I-residue_number"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-bond_interaction": 29,
+    "B-chemical": 1,
+    "B-complex_assembly": 21,
+    "B-evidence": 12,
+    "B-experimental_method": 8,
+    "B-gene": 3,
+    "B-mutant": 25,
+    "B-oligomeric_state": 27,
+    "B-protein": 14,
+    "B-protein_state": 16,
+    "B-protein_type": 7,
+    "B-ptm": 24,
+    "B-residue_name": 33,
+    "B-residue_name_number": 28,
+    "B-residue_number": 34,
+    "B-residue_range": 31,
+    "B-site": 17,
+    "B-species": 2,
+    "B-structure_element": 19,
+    "B-taxonomy_domain": 5,
+    "I-bond_interaction": 30,
+    "I-chemical": 6,
+    "I-complex_assembly": 23,
+    "I-evidence": 13,
+    "I-experimental_method": 9,
+    "I-gene": 4,
+    "I-mutant": 26,
+    "I-oligomeric_state": 37,
+    "I-protein": 15,
+    "I-protein_state": 22,
+    "I-protein_type": 10,
+    "I-ptm": 35,
+    "I-residue_name": 39,
+    "I-residue_name_number": 38,
+    "I-residue_number": 40,
+    "I-residue_range": 32,
+    "I-site": 18,
+    "I-species": 11,
+    "I-structure_element": 20,
+    "I-taxonomy_domain": 36,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744e186d0636f3c811a9fdfa80e5eaad38f89240a3afdde8d0762f2db0206dc9
+size 435764845

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}