Update models to support DeLFT 0.4.x.

dataseer-binary_bert/config.json

@@ -0,0 +1,19 @@
+{
+    "model_name": "dataseer-binary_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "dataset",
+        "no_dataset"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-binary_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeaa9b9ffc0b1e231712b6ee26a8cc784309046b1be938b73a057f0352ed671
+size 440033552

dataseer-binary_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-binary_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-binary_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

dataseer-first_bert/config.json

@@ -0,0 +1,42 @@
+{
+    "model_name": "dataseer-first_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "calorimetry",
+        "chromatography",
+        "coulombimetry data",
+        "densitometry",
+        "electrocardiograph",
+        "electroencephalogram",
+        "electromyography",
+        "electrooculography",
+        "electrophysiology",
+        "electroretinography",
+        "emission flame photometry",
+        "flow cytometry",
+        "genetic data",
+        "image",
+        "mass spectrometry",
+        "no_dataset",
+        "protein data",
+        "sound data",
+        "spectrometry",
+        "spectrum analysis",
+        "systematic review",
+        "tabular data",
+        "video recording",
+        "voltammetry data",
+        "x-ray diffraction data"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-first_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d752987b9c721a5029f34dbb8ca6ffddc3a7771e43a10fcf337277eb8d617bed
+size 440104208

dataseer-first_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-first_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-first_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

dataseer-reuse_bert/config.json

@@ -0,0 +1,19 @@
+{
+    "model_name": "dataseer-reuse_bert",
+    "architecture": "bert",
+    "embeddings_name": null,
+    "char_embedding_size": 25,
+    "word_embedding_size": 0,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.25,
+    "maxlen": 300,
+    "dense_size": 32,
+    "use_char_feature": false,
+    "list_classes": [
+        "no_reuse",
+        "reuse"
+    ],
+    "fold_number": 1,
+    "batch_size": 16,
+    "transformer_name": "allenai/scibert_scivocab_cased"
+}

dataseer-reuse_bert/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2ac521d885359729cf7b1b59703d4c76faa3f32c6dc0d4aaad660d54982bdb
+size 440033552

dataseer-reuse_bert/transformer-config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

dataseer-reuse_bert/transformer-tokenizer/special_tokens_map.json

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

dataseer-reuse_bert/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

datasets-BERT_CRF/config.json

@@ -0,0 +1,36 @@
+{
+    "model_name": "datasets-BERT_CRF",
+    "architecture": "BERT_CRF",
+    "embeddings_name": null,
+    "char_vocab_size": 234,
+    "case_vocab_size": 8,
+    "char_embedding_size": 25,
+    "num_char_lstm_units": 25,
+    "max_char_length": 30,
+    "features_vocabulary_size": 12,
+    "features_indices": null,
+    "features_embedding_size": 4,
+    "features_lstm_units": 4,
+    "max_sequence_length": 200,
+    "word_embedding_size": 0,
+    "num_word_lstm_units": 100,
+    "case_embedding_size": 5,
+    "dropout": 0.5,
+    "recurrent_dropout": 0.5,
+    "use_crf": true,
+    "use_chain_crf": false,
+    "fold_number": 1,
+    "batch_size": 20,
+    "transformer_name": "michiyasunaga/LinkBERT-base",
+    "use_ELMo": false,
+    "labels": {
+        "<PAD>": 0,
+        "B-data_device": 1,
+        "B-dataset": 2,
+        "B-dataset_name": 3,
+        "I-data_device": 4,
+        "I-dataset": 5,
+        "I-dataset_name": 6,
+        "O": 7
+    }
+}

datasets-BERT_CRF/model_weights.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a6fb1634bf6dbb8749eef1daeeda4655aaa8a2836fd64563684e7e98bcd50a
+size 433539664

datasets-BERT_CRF/preprocessor.json

@@ -0,0 +1,277 @@
+{
+    "padding": true,
+    "return_lengths": false,
+    "return_word_embeddings": false,
+    "return_casing": false,
+    "return_features": false,
+    "return_chars": false,
+    "return_bert_embeddings": true,
+    "vocab_char": {
+        "<PAD>": 0,
+        "<UNK>": 1,
+        "!": 2,
+        "\"": 3,
+        "#": 4,
+        "$": 5,
+        "%": 6,
+        "&": 7,
+        "'": 8,
+        "(": 9,
+        ")": 10,
+        "*": 11,
+        "+": 12,
+        ",": 13,
+        "-": 14,
+        ".": 15,
+        "/": 16,
+        "0": 17,
+        "1": 18,
+        "2": 19,
+        "3": 20,
+        "4": 21,
+        "5": 22,
+        "6": 23,
+        "7": 24,
+        "8": 25,
+        "9": 26,
+        ":": 27,
+        ";": 28,
+        "<": 29,
+        "=": 30,
+        ">": 31,
+        "?": 32,
+        "@": 33,
+        "A": 34,
+        "B": 35,
+        "C": 36,
+        "D": 37,
+        "E": 38,
+        "F": 39,
+        "G": 40,
+        "H": 41,
+        "I": 42,
+        "J": 43,
+        "K": 44,
+        "L": 45,
+        "M": 46,
+        "N": 47,
+        "O": 48,
+        "P": 49,
+        "Q": 50,
+        "R": 51,
+        "S": 52,
+        "T": 53,
+        "U": 54,
+        "V": 55,
+        "W": 56,
+        "X": 57,
+        "Y": 58,
+        "Z": 59,
+        "[": 60,
+        "\\": 61,
+        "]": 62,
+        "^": 63,
+        "_": 64,
+        "`": 65,
+        "a": 66,
+        "b": 67,
+        "c": 68,
+        "d": 69,
+        "e": 70,
+        "f": 71,
+        "g": 72,
+        "h": 73,
+        "i": 74,
+        "j": 75,
+        "k": 76,
+        "l": 77,
+        "m": 78,
+        "n": 79,
+        "o": 80,
+        "p": 81,
+        "q": 82,
+        "r": 83,
+        "s": 84,
+        "t": 85,
+        "u": 86,
+        "v": 87,
+        "w": 88,
+        "x": 89,
+        "y": 90,
+        "z": 91,
+        "{": 92,
+        "|": 93,
+        "}": 94,
+        "~": 95,
+        "\u00a1": 96,
+        "\u00a2": 97,
+        "\u00a4": 98,
+        "\u00a7": 99,
+        "\u00a8": 100,
+        "\u00ae": 101,
+        "\u00b0": 102,
+        "\u00b1": 103,
+        "\u00b4": 104,
+        "\u00b5": 105,
+        "\u00b7": 106,
+        "\u00bc": 107,
+        "\u00bd": 108,
+        "\u00c2": 109,
+        "\u00c4": 110,
+        "\u00c5": 111,
+        "\u00c9": 112,
+        "\u00d2": 113,
+        "\u00d5": 114,
+        "\u00d7": 115,
+        "\u00d8": 116,
+        "\u00de": 117,
+        "\u00df": 118,
+        "\u00e1": 119,
+        "\u00e2": 120,
+        "\u00e3": 121,
+        "\u00e4": 122,
+        "\u00e5": 123,
+        "\u00e7": 124,
+        "\u00e9": 125,
+        "\u00ea": 126,
+        "\u00ed": 127,
+        "\u00ef": 128,
+        "\u00f0": 129,
+        "\u00f1": 130,
+        "\u00f3": 131,
+        "\u00f4": 132,
+        "\u00f8": 133,
+        "\u00fc": 134,
+        "\u0109": 135,
+        "\u012a": 136,
+        "\u012b": 137,
+        "\u0131": 138,
+        "\u0142": 139,
+        "\u015d": 140,
+        "\u0177": 141,
+        "\u017b": 142,
+        "\u017e": 143,
+        "\u01eb": 144,
+        "\u0219": 145,
+        "\u0263": 146,
+        "\u02da": 147,
+        "\u02dd": 148,
+        "\u0387": 149,
+        "\u0394": 150,
+        "\u0398": 151,
+        "\u039b": 152,
+        "\u03a3": 153,
+        "\u03a6": 154,
+        "\u03a8": 155,
+        "\u03b1": 156,
+        "\u03b2": 157,
+        "\u03b3": 158,
+        "\u03b4": 159,
+        "\u03b5": 160,
+        "\u03b6": 161,
+        "\u03b7": 162,
+        "\u03b8": 163,
+        "\u03ba": 164,
+        "\u03bb": 165,
+        "\u03bc": 166,
+        "\u03bd": 167,
+        "\u03be": 168,
+        "\u03c0": 169,
+        "\u03c1": 170,
+        "\u03c3": 171,
+        "\u03c4": 172,
+        "\u03c5": 173,
+        "\u03c6": 174,
+        "\u03c7": 175,
+        "\u03c8": 176,
+        "\u03c9": 177,
+        "\u03d5": 178,
+        "\u03f5": 179,
+        "\u0434": 180,
+        "\u0740": 181,
+        "\u0742": 182,
+        "\u0750": 183,
+        "\u0751": 184,
+        "\u0753": 185,
+        "\u123a": 186,
+        "\u123b": 187,
+        "\u1ef9": 188,
+        "\u2016": 189,
+        "\u2019": 190,
+        "\u2022": 191,
+        "\u2026": 192,
+        "\u202a": 193,
+        "\u202b": 194,
+        "\u202c": 195,
+        "\u2032": 196,
+        "\u2033": 197,
+        "\u2113": 198,
+        "\u211d": 199,
+        "\u2122": 200,
+        "\u2126": 201,
+        "\u212b": 202,
+        "\u2190": 203,
+        "\u2192": 204,
+        "\u2194": 205,
+        "\u21e1": 206,
+        "\u21e5": 207,
+        "\u2200": 208,
+        "\u2202": 209,
+        "\u2206": 210,
+        "\u2208": 211,
+        "\u2212": 212,
+        "\u221a": 213,
+        "\u221d": 214,
+        "\u221e": 215,
+        "\u222a": 216,
+        "\u223c": 217,
+        "\u2248": 218,
+        "\u2264": 219,
+        "\u2265": 220,
+        "\u226a": 221,
+        "\u2282": 222,
+        "\u2286": 223,
+        "\u22a5": 224,
+        "\u2303": 225,
+        "\u23af": 226,
+        "\u25b3": 227,
+        "\u27e8": 228,
+        "\u27e9": 229,
+        "\uf071": 230,
+        "\uf0a2": 231,
+        "\uf731": 232,
+        "\ufffd": 233
+    },
+    "vocab_tag": {
+        "<PAD>": 0,
+        "B-data_device": 1,
+        "B-dataset": 2,
+        "B-dataset_name": 3,
+        "I-data_device": 4,
+        "I-dataset": 5,
+        "I-dataset_name": 6,
+        "O": 7
+    },
+    "vocab_case": [
+        "<PAD>",
+        "numeric",
+        "allLower",
+        "allUpper",
+        "initialUpper",
+        "other",
+        "mainly_numeric",
+        "contains_digit"
+    ],
+    "max_char_length": 30,
+    "feature_preprocessor": null,
+    "indice_tag": {
+        "0": "<PAD>",
+        "1": "B-data_device",
+        "2": "B-dataset",
+        "3": "B-dataset_name",
+        "4": "I-data_device",
+        "5": "I-dataset",
+        "6": "I-dataset_name",
+        "7": "O"
+    }
+}

datasets-BERT_CRF/transformer-config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "michiyasunaga/LinkBERT-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

datasets-BERT_CRF/transformer-tokenizer/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

datasets-BERT_CRF/transformer-tokenizer/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}