Upload 7 files
Browse files- config.json +59 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./pretrained-models/TCMRoBERTa",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-\u6765\u6e90",
|
17 |
+
"2": "I-\u6765\u6e90",
|
18 |
+
"3": "B-\u65b9\u5242",
|
19 |
+
"4": "I-\u65b9\u5242",
|
20 |
+
"5": "B-\u8bc1\u578b",
|
21 |
+
"6": "I-\u8bc1\u578b",
|
22 |
+
"7": "B-\u75c5\u540d",
|
23 |
+
"8": "I-\u75c5\u540d",
|
24 |
+
"9": "B-\u75c7\u72b6",
|
25 |
+
"10": "I-\u75c7\u72b6",
|
26 |
+
"11": "B-\u672c\u8349",
|
27 |
+
"12": "I-\u672c\u8349"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-\u65b9\u5242": 3,
|
33 |
+
"B-\u672c\u8349": 11,
|
34 |
+
"B-\u6765\u6e90": 1,
|
35 |
+
"B-\u75c5\u540d": 7,
|
36 |
+
"B-\u75c7\u72b6": 9,
|
37 |
+
"B-\u8bc1\u578b": 5,
|
38 |
+
"I-\u65b9\u5242": 4,
|
39 |
+
"I-\u672c\u8349": 12,
|
40 |
+
"I-\u6765\u6e90": 2,
|
41 |
+
"I-\u75c5\u540d": 8,
|
42 |
+
"I-\u75c7\u72b6": 10,
|
43 |
+
"I-\u8bc1\u578b": 6,
|
44 |
+
"O": 0
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-05,
|
47 |
+
"max_position_embeddings": 514,
|
48 |
+
"model_type": "roberta",
|
49 |
+
"num_attention_heads": 12,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.26.1",
|
56 |
+
"type_vocab_size": 1,
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 26318
|
59 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0845ff75b9c5688d857049660691bca57fd8c5e67559f294b0e307a539115717
|
3 |
+
size 422766001
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "./pretrained-models/TCMRoBERTa",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72409eac51e703990de897280f7e3b8c3ab9f8718697574047535a456fa01d26
|
3 |
+
size 3439
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|