Upload 5 files
Browse files- config.json +61 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hfl/chinese-roberta-wwm-ext",
|
3 |
+
"architectures": [
|
4 |
+
"GlobalPointerForNer"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"decode_thresh": 0.0,
|
10 |
+
"directionality": "bidi",
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"head_size": 64,
|
13 |
+
"head_type": "efficient_global_pointer",
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "LABEL_0",
|
19 |
+
"1": "LABEL_1",
|
20 |
+
"2": "LABEL_2",
|
21 |
+
"3": "LABEL_3",
|
22 |
+
"4": "LABEL_4",
|
23 |
+
"5": "LABEL_5",
|
24 |
+
"6": "LABEL_6",
|
25 |
+
"7": "LABEL_7",
|
26 |
+
"8": "LABEL_8"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"is_sparse": false,
|
31 |
+
"label2id": {
|
32 |
+
"bod": 0,
|
33 |
+
"dep": 1,
|
34 |
+
"dis": 2,
|
35 |
+
"dru": 3,
|
36 |
+
"equ": 4,
|
37 |
+
"ite": 5,
|
38 |
+
"mic": 6,
|
39 |
+
"pro": 7,
|
40 |
+
"sym": 8
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-12,
|
43 |
+
"max_position_embeddings": 512,
|
44 |
+
"model_type": "bert",
|
45 |
+
"num_attention_heads": 12,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"output_past": true,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"pooler_fc_size": 768,
|
50 |
+
"pooler_num_attention_heads": 12,
|
51 |
+
"pooler_num_fc_layers": 3,
|
52 |
+
"pooler_size_per_head": 128,
|
53 |
+
"pooler_type": "first_token_transform",
|
54 |
+
"position_embedding_type": "absolute",
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.24.0",
|
57 |
+
"type_vocab_size": 2,
|
58 |
+
"use_cache": true,
|
59 |
+
"use_rope": true,
|
60 |
+
"vocab_size": 21128
|
61 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"name_or_path": "hfl/chinese-roberta-wwm-ext",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": "/home/xusenlin/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext/snapshots/5c58d0b8ec1d9014354d691c538661bf00bfdb44/special_tokens_map.json",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|