Added Chunking tagging model
Browse files- config.json +74 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "B-ADJP",
|
13 |
+
"1": "B-ADVP",
|
14 |
+
"2": "B-CONJP",
|
15 |
+
"3": "B-INTJ",
|
16 |
+
"4": "B-LST",
|
17 |
+
"5": "B-NP",
|
18 |
+
"6": "B-PP",
|
19 |
+
"7": "B-PRT",
|
20 |
+
"8": "B-SBAR",
|
21 |
+
"9": "B-UCP",
|
22 |
+
"10": "B-VP",
|
23 |
+
"11": "I-ADJP",
|
24 |
+
"12": "I-ADVP",
|
25 |
+
"13": "I-CONJP",
|
26 |
+
"14": "I-INTJ",
|
27 |
+
"15": "I-LST",
|
28 |
+
"16": "I-NP",
|
29 |
+
"17": "I-PP",
|
30 |
+
"18": "I-PRT",
|
31 |
+
"19": "I-SBAR",
|
32 |
+
"20": "I-UCP",
|
33 |
+
"21": "I-VP",
|
34 |
+
"22": "O"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"B-ADJP": 0,
|
40 |
+
"B-ADVP": 1,
|
41 |
+
"B-CONJP": 2,
|
42 |
+
"B-INTJ": 3,
|
43 |
+
"B-LST": 4,
|
44 |
+
"B-NP": 5,
|
45 |
+
"B-PP": 6,
|
46 |
+
"B-PRT": 7,
|
47 |
+
"B-SBAR": 8,
|
48 |
+
"B-UCP": 9,
|
49 |
+
"B-VP": 10,
|
50 |
+
"I-ADJP": 11,
|
51 |
+
"I-ADVP": 12,
|
52 |
+
"I-CONJP": 13,
|
53 |
+
"I-INTJ": 14,
|
54 |
+
"I-LST": 15,
|
55 |
+
"I-NP": 16,
|
56 |
+
"I-PP": 17,
|
57 |
+
"I-PRT": 18,
|
58 |
+
"I-SBAR": 19,
|
59 |
+
"I-UCP": 20,
|
60 |
+
"I-VP": 21,
|
61 |
+
"O": 22
|
62 |
+
},
|
63 |
+
"layer_norm_eps": 1e-12,
|
64 |
+
"max_position_embeddings": 512,
|
65 |
+
"model_type": "bert",
|
66 |
+
"num_attention_heads": 12,
|
67 |
+
"num_hidden_layers": 12,
|
68 |
+
"pad_token_id": 0,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"transformers_version": "4.6.1",
|
71 |
+
"type_vocab_size": 2,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 28996
|
74 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35e8d6c5f8e92dce15138c4a9fcf4d86b211358067bd29a69559f4b66aeb39db
|
3 |
+
size 431038007
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62f0f4ebbdacd9978f9696254fc02cc9a274041d5d53cef7e2469444cfbd2488
|
3 |
+
size 2415
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|