ikuyamada commited on
Commit
4a5b9b8
1 Parent(s): 9e762eb

Initial commit

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<ent>": 32770, "<ent2>": 32771}
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/luke-japanese/hf_xlm_roberta",
3
+ "architectures": [
4
+ "LukeForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_entity_prediction": false,
11
+ "entity_emb_size": 256,
12
+ "entity_vocab_size": 4,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 514,
21
+ "model_type": "luke",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.13.0",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "use_entity_aware_attention": true,
31
+ "vocab_size": 32772
32
+ }
entity_vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[MASK]": 0, "[UNK]": 1, "[PAD]": 2, "[MASK2]": 3}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe47333f008a3a95a63574dd37eb0d27f60e204a90101e9968f7a2b41b68a1f
3
+ size 535665411
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
3
+ size 841889
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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/hf_xlm_roberta/special_tokens_map.json", "name_or_path": "models/luke-japanese/hf_luke_japanese_lite_epoch20", "tokenizer_file": "models/luke-japanese/hf_luke_japanese_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"}