Upload 7 files
Browse files- .gitattributes +1 -0
- config.json +83 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
vocab.txt filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"id2label": {
|
11 |
+
"0": "B-ANG",
|
12 |
+
"1": "B-DUC",
|
13 |
+
"2": "B-EVE",
|
14 |
+
"3": "B-FAC",
|
15 |
+
"4": "B-GPE",
|
16 |
+
"5": "B-LOC",
|
17 |
+
"6": "B-ORG",
|
18 |
+
"7": "B-PER",
|
19 |
+
"8": "B-WOA",
|
20 |
+
"9": "B-INFORMAL",
|
21 |
+
"10": "B-MISC",
|
22 |
+
"11": "B-TIMEX",
|
23 |
+
"12": "B-TTL",
|
24 |
+
"13": "I-DUC",
|
25 |
+
"14": "I-EVE",
|
26 |
+
"15": "I-FAC",
|
27 |
+
"16": "I-GPE",
|
28 |
+
"17": "I-LOC",
|
29 |
+
"18": "I-ORG",
|
30 |
+
"19": "I-PER",
|
31 |
+
"20": "I-WOA",
|
32 |
+
"21": "I-ANG",
|
33 |
+
"22": "I-INFORMAL",
|
34 |
+
"23": "I-MISC",
|
35 |
+
"24": "I-TIMEX",
|
36 |
+
"25": "I-TTL",
|
37 |
+
"26": "O"
|
38 |
+
},
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 4096,
|
41 |
+
"label2id": {
|
42 |
+
"B-ANG": 0,
|
43 |
+
"B-DUC": 1,
|
44 |
+
"B-EVE": 2,
|
45 |
+
"B-FAC": 3,
|
46 |
+
"B-GPE": 4,
|
47 |
+
"B-INFORMAL": 9,
|
48 |
+
"B-LOC": 5,
|
49 |
+
"B-MISC": 10,
|
50 |
+
"B-ORG": 6,
|
51 |
+
"B-PER": 7,
|
52 |
+
"B-TIMEX": 11,
|
53 |
+
"B-TTL": 12,
|
54 |
+
"B-WOA": 8,
|
55 |
+
"I-ANG": 21,
|
56 |
+
"I-DUC": 13,
|
57 |
+
"I-EVE": 14,
|
58 |
+
"I-FAC": 15,
|
59 |
+
"I-GPE": 16,
|
60 |
+
"I-INFORMAL": 22,
|
61 |
+
"I-LOC": 17,
|
62 |
+
"I-MISC": 23,
|
63 |
+
"I-ORG": 18,
|
64 |
+
"I-PER": 19,
|
65 |
+
"I-TIMEX": 24,
|
66 |
+
"I-TTL": 25,
|
67 |
+
"I-WOA": 20,
|
68 |
+
"O": 26
|
69 |
+
},
|
70 |
+
"layer_norm_eps": 1e-12,
|
71 |
+
"max_position_embeddings": 512,
|
72 |
+
"model_type": "bert",
|
73 |
+
"newmodern": true,
|
74 |
+
"num_attention_heads": 16,
|
75 |
+
"num_hidden_layers": 24,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.36.2",
|
80 |
+
"type_vocab_size": 2,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 128000
|
83 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:763e556ec1c0dd676f48c9b306aec90bb11322f682f0c3d0de9574c01ba10272
|
3 |
+
size 1735796812
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d96a273e636d9fade2fdcfe0d25aaa15491bf63926d8aef31b49705d79af790c
|
3 |
+
size 1735905894
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
|
3 |
+
size 1500244
|