Initial commit

added_tokens.json

@@ -0,0 +1 @@
+{"<ent>": 32770, "<ent2>": 32771}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "models/luke-japanese-large/hf_xlm_roberta",
+  "architectures": [
+    "LukeForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese-large/hf_xlm_roberta",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

entity_vocab.json

@@ -0,0 +1 @@
+{"[MASK]": 0, "[UNK]": 1, "[PAD]": 2, "[MASK2]": 3}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbd147cc39aeedf80f05b5cfb8935c252184b85d84c5a1e06058a17bbc48955
+size 1660841459

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
+size 841889

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": [{"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "task": null, "max_entity_length": 32, "max_mention_length": 30, "entity_token_1": {"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "entity_token_2": {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": "models/luke-japanese-large/hf_xlm_roberta/special_tokens_map.json", "name_or_path": "models/luke-japanese-large/hf_luke_japanese_large_lite_epoch20", "tokenizer_file": "models/luke-japanese-large/hf_luke_japanese_large_lite_epoch20/tokenizer.json", "additional_special_tokens": [{"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}], "tokenizer_class": "MLukeTokenizer"}