Add delft 0.4.6 load scaffold for material-BERT_CRF (preprocessor.json + transformer config/tokenizer; no retrain) (#2)

- Add delft 0.4.6 load scaffold for material-BERT_CRF (preprocessor.json + transformer config/tokenizer; no retrain) (4f7a5e76b663b2c3cc1fa5ca399975ce56e70e84)

material-BERT_CRF/config.json

@@ -0,0 +1,46 @@
+{
+    "model_name": "material-BERT_CRF",
+    "architecture": "BERT_CRF",
+    "embeddings_name": null,
+    "char_vocab_size": 123,
+    "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": 512,
+    "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": 30,
+    "transformer_name": "allenai/scibert_scivocab_cased/dir",
+    "use_ELMo": false,
+    "labels": {
+        "<PAD>": 0,
+        "B-<doping>": 1,
+        "B-<fabrication>": 2,
+        "B-<formula>": 3,
+        "B-<name>": 4,
+        "B-<shape>": 5,
+        "B-<substrate>": 6,
+        "B-<value>": 7,
+        "B-<variable>": 8,
+        "I-<doping>": 9,
+        "I-<fabrication>": 10,
+        "I-<formula>": 11,
+        "I-<name>": 12,
+        "I-<shape>": 13,
+        "I-<substrate>": 14,
+        "I-<value>": 15,
+        "I-<variable>": 16,
+        "O": 17
+    }
+}

material-BERT_CRF/preprocessor.json

@@ -0,0 +1,65 @@
+{
+    "padding": true,
+    "return_lengths": true,
+    "return_word_embeddings": false,
+    "return_casing": false,
+    "return_features": false,
+    "return_chars": false,
+    "return_bert_embeddings": true,
+    "vocab_char": {
+        "<PAD>": 0,
+        "<UNK>": 1
+    },
+    "vocab_tag": {
+        "<PAD>": 0,
+        "B-<doping>": 1,
+        "B-<fabrication>": 2,
+        "B-<formula>": 3,
+        "B-<name>": 4,
+        "B-<shape>": 5,
+        "B-<substrate>": 6,
+        "B-<value>": 7,
+        "B-<variable>": 8,
+        "I-<doping>": 9,
+        "I-<fabrication>": 10,
+        "I-<formula>": 11,
+        "I-<name>": 12,
+        "I-<shape>": 13,
+        "I-<substrate>": 14,
+        "I-<value>": 15,
+        "I-<variable>": 16,
+        "O": 17
+    },
+    "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-<doping>",
+        "2": "B-<fabrication>",
+        "3": "B-<formula>",
+        "4": "B-<name>",
+        "5": "B-<shape>",
+        "6": "B-<substrate>",
+        "7": "B-<value>",
+        "8": "B-<variable>",
+        "9": "I-<doping>",
+        "10": "I-<fabrication>",
+        "11": "I-<formula>",
+        "12": "I-<name>",
+        "13": "I-<shape>",
+        "14": "I-<substrate>",
+        "15": "I-<value>",
+        "16": "I-<variable>",
+        "17": "O"
+    }
+}

material-BERT_CRF/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": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31116
+}

material-BERT_CRF/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]"
+}

material-BERT_CRF/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]"
+}