model/tokenizer: add initial version

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 32001,
+  "<start>": 32000
+}

config.json

@@ -0,0 +1,201 @@
+{
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "gwlms/bert-base-dewiki-v1",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "O",
+      "1": "B-LOC",
+      "2": "I-LOC",
+      "3": "B-LOCderiv",
+      "4": "I-LOCderiv",
+      "5": "B-LOCpart",
+      "6": "I-LOCpart",
+      "7": "B-ORG",
+      "8": "I-ORG",
+      "9": "B-ORGderiv",
+      "10": "I-ORGderiv",
+      "11": "B-ORGpart",
+      "12": "I-ORGpart",
+      "13": "B-OTH",
+      "14": "I-OTH",
+      "15": "B-OTHderiv",
+      "16": "I-OTHderiv",
+      "17": "B-OTHpart",
+      "18": "I-OTHpart",
+      "19": "B-PER",
+      "20": "I-PER",
+      "21": "B-PERderiv",
+      "22": "I-PERderiv",
+      "23": "B-PERpart",
+      "24": "I-PERpart"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-LOC": 1,
+      "B-LOCderiv": 3,
+      "B-LOCpart": 5,
+      "B-ORG": 7,
+      "B-ORGderiv": 9,
+      "B-ORGpart": 11,
+      "B-OTH": 13,
+      "B-OTHderiv": 15,
+      "B-OTHpart": 17,
+      "B-PER": 19,
+      "B-PERderiv": 21,
+      "B-PERpart": 23,
+      "I-LOC": 2,
+      "I-LOCderiv": 4,
+      "I-LOCpart": 6,
+      "I-ORG": 8,
+      "I-ORGderiv": 10,
+      "I-ORGpart": 12,
+      "I-OTH": 14,
+      "I-OTHderiv": 16,
+      "I-OTHpart": 18,
+      "I-PER": 20,
+      "I-PERderiv": 22,
+      "I-PERpart": 24,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.31.0",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32002
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "LOC",
+    "2": "LOCderiv",
+    "3": "LOCpart",
+    "4": "ORG",
+    "5": "ORGderiv",
+    "6": "ORGpart",
+    "7": "OTH",
+    "8": "OTHderiv",
+    "9": "OTHpart",
+    "10": "PER",
+    "11": "PERderiv",
+    "12": "PERpart"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 1,
+    "2": 1,
+    "3": 2,
+    "4": 2,
+    "5": 3,
+    "6": 3,
+    "7": 4,
+    "8": 4,
+    "9": 5,
+    "10": 5,
+    "11": 6,
+    "12": 6,
+    "13": 7,
+    "14": 7,
+    "15": 8,
+    "16": 8,
+    "17": 9,
+    "18": 9,
+    "19": 10,
+    "20": 10,
+    "21": 11,
+    "22": 11,
+    "23": 12,
+    "24": 12
+  },
+  "label2id": {
+    "LOC": 1,
+    "LOCderiv": 2,
+    "LOCpart": 3,
+    "O": 0,
+    "ORG": 4,
+    "ORGderiv": 5,
+    "ORGpart": 6,
+    "OTH": 7,
+    "OTHderiv": 8,
+    "OTHpart": 9,
+    "PER": 10,
+    "PERderiv": 11,
+    "PERpart": 12
+  },
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 256,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.2.4",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.31.0",
+  "vocab_size": 32002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7755854af3e045f36cfe32261996cfdee4080b141720a0a374b0e347e811d8c2
+size 442624369

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 +1,19 @@
+{
+  "add_prefix_space": true,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "entity_max_length": 8,
+  "marker_max_length": 128,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ea8f2c4d524bc7fc02f0b1c324710d7157570d110206b795d177bde50e11a6
+size 4027