initial commit
Browse files- added_tokens.json +1 -0
- config.json +49 -0
- entity_vocab.json +1 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<ent>": 250002, "<ent2>": 250003}
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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 |
+
"id2label": {
|
19 |
+
"0": "O",
|
20 |
+
"1": "LOC",
|
21 |
+
"2": "PER",
|
22 |
+
"3": "ORG",
|
23 |
+
"4": "MISC"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"O": 0,
|
29 |
+
"LOC": 1,
|
30 |
+
"PER": 2,
|
31 |
+
"ORG": 3,
|
32 |
+
"MISC": 4
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-05,
|
35 |
+
"max_position_embeddings": 514,
|
36 |
+
"model_type": "luke",
|
37 |
+
"num_attention_heads": 16,
|
38 |
+
"num_hidden_layers": 24,
|
39 |
+
"output_past": true,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.15.0",
|
44 |
+
"type_vocab_size": 1,
|
45 |
+
"use_cache": true,
|
46 |
+
"use_deepspeed_transformer_layer": false,
|
47 |
+
"use_entity_aware_attention": false,
|
48 |
+
"vocab_size": 250004
|
49 |
+
}
|
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:cb63581138acef65b6b070eb6630c82583405fd88c4d033d37ec4299880c1089
|
3 |
+
size 2242955811
|
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-lite", "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"}, {"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_file": null, "tokenizer_class": "MLukeTokenizer"}
|