ryo0634 commited on
Commit
7da2d65
1 Parent(s): 15795bf

Initial commit

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<ent>": 250002, "<ent2>": 250003}
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "studio-ousia/mluke-large-lite",
3
+ "architectures": [
4
+ "LukeForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bert_model_name": "xlm-roberta-large",
8
+ "bos_token_id": 0,
9
+ "cls_entity_prediction": false,
10
+ "deepspeed_transformer_layer_args": {},
11
+ "entity_emb_size": 256,
12
+ "entity_vocab_size": 4,
13
+ "eos_token_id": 2,
14
+ "gradient_checkpointing": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 1024,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "luke",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 24,
25
+ "output_past": true,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.15.0",
30
+ "type_vocab_size": 1,
31
+ "use_cache": true,
32
+ "use_deepspeed_transformer_layer": false,
33
+ "use_entity_aware_attention": true,
34
+ "vocab_size": 250004
35
+ }
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 sha256:41e838fbf2ebc1ece85fb8bdbc6156d2d3075db5660d7eb8c4f497d5753fee4a
3
+ size 2551492659
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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": true}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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"}, "entity_unk_token": "[UNK]", "entity_pad_token": "[PAD]", "entity_mask_token": "[MASK]", "entity_mask2_token": "[MASK2]", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "studio-ousia/mluke-large", "tokenizer_file": null, "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"}