Hugging Face's logo

naist-nlp
/
mluke-large-lite-finetuned-atd

PyTorch
luke
Model card Files Community
2
chantera commited on
Commit
41ca7de
•
1 Parent(s): b339965

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -0
  2. config.json +66 -0
  3. entity_vocab.json +6 -0
  4. pytorch_model.bin +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +31 -0
  7. tokenizer_config.json +78 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ent2>": 250003,
3
+ "<ent>": 250002
4
+ }
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "studio-ousia/mluke-large-lite",
3
+ "architectures": [
4
+ "LukeForEntitySpanClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bert_model_name": "xlm-roberta-large",
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_entity_prediction": false,
11
+ "deepspeed_transformer_layer_args": {},
12
+ "entity_emb_size": 256,
13
+ "entity_vocab_size": 4,
14
+ "eos_token_id": 2,
15
+ "gradient_checkpointing": false,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.1,
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "<none>",
21
+ "1": "DEICTIC",
22
+ "2": "FAC_NAME",
23
+ "3": "FAC_NOM",
24
+ "4": "FAC_ORG",
25
+ "5": "LINE_NAME",
26
+ "6": "LINE_NOM",
27
+ "7": "LOC_NAME",
28
+ "8": "LOC_NOM",
29
+ "9": "LOC_ORG",
30
+ "10": "LOC_OR_FAC",
31
+ "11": "TRANS_NAME",
32
+ "12": "TRANS_NOM"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 4096,
36
+ "label2id": {
37
+ "<none>": 0,
38
+ "DEICTIC": 1,
39
+ "FAC_NAME": 2,
40
+ "FAC_NOM": 3,
41
+ "FAC_ORG": 4,
42
+ "LINE_NAME": 5,
43
+ "LINE_NOM": 6,
44
+ "LOC_NAME": 7,
45
+ "LOC_NOM": 8,
46
+ "LOC_ORG": 9,
47
+ "LOC_OR_FAC": 10,
48
+ "TRANS_NAME": 11,
49
+ "TRANS_NOM": 12
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_position_embeddings": 514,
53
+ "model_type": "luke",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "output_past": true,
57
+ "pad_token_id": 1,
58
+ "position_embedding_type": "absolute",
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.30.1",
61
+ "type_vocab_size": 1,
62
+ "use_cache": true,
63
+ "use_deepspeed_transformer_layer": false,
64
+ "use_entity_aware_attention": false,
65
+ "vocab_size": 250004
66
+ }
entity_vocab.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "[MASK2]": 3,
3
+ "[MASK]": 0,
4
+ "[PAD]": 2,
5
+ "[UNK]": 1
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0e41f923e2a3b402f36b7f0eb4ac63a54676106666a369866cfcd50091a622
3
+ size 2243036425
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<ent>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<ent2>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "cls_token": "<s>",
20
+ "eos_token": "</s>",
21
+ "mask_token": {
22
+ "content": "<mask>",
23
+ "lstrip": true,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": "<pad>",
29
+ "sep_token": "</s>",
30
+ "unk_token": "<unk>"
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "__type": "AddedToken",
5
+ "content": "<ent>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ {
12
+ "__type": "AddedToken",
13
+ "content": "<ent2>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ {
20
+ "__type": "AddedToken",
21
+ "content": "<ent>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ {
28
+ "__type": "AddedToken",
29
+ "content": "<ent2>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ ],
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "cls_token": "<s>",
39
+ "entity_mask2_token": "[MASK2]",
40
+ "entity_mask_token": "[MASK]",
41
+ "entity_pad_token": "[PAD]",
42
+ "entity_token_1": {
43
+ "__type": "AddedToken",
44
+ "content": "<ent>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false
49
+ },
50
+ "entity_token_2": {
51
+ "__type": "AddedToken",
52
+ "content": "<ent2>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ "entity_unk_token": "[UNK]",
59
+ "eos_token": "</s>",
60
+ "mask_token": {
61
+ "__type": "AddedToken",
62
+ "content": "<mask>",
63
+ "lstrip": true,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "max_entity_length": 64,
69
+ "max_mention_length": 16,
70
+ "model_max_length": 512,
71
+ "pad_token": "<pad>",
72
+ "sep_token": "</s>",
73
+ "sp_model_kwargs": {},
74
+ "task": "entity_span_classification",
75
+ "tokenizer_class": "MLukeTokenizer",
76
+ "tokenizer_file": null,
77
+ "unk_token": "<unk>"
78
+ }