Upload 8 files
Browse files- added_tokens.json +3 -0
- config.json +65 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"id2label": {
|
11 |
+
"0": "B-EMAIL",
|
12 |
+
"1": "B-ID_NUM",
|
13 |
+
"2": "B-NAME_STUDENT",
|
14 |
+
"3": "B-PHONE_NUM",
|
15 |
+
"4": "B-STREET_ADDRESS",
|
16 |
+
"5": "B-URL_PERSONAL",
|
17 |
+
"6": "B-USERNAME",
|
18 |
+
"7": "I-ID_NUM",
|
19 |
+
"8": "I-NAME_STUDENT",
|
20 |
+
"9": "I-PHONE_NUM",
|
21 |
+
"10": "I-STREET_ADDRESS",
|
22 |
+
"11": "I-URL_PERSONAL",
|
23 |
+
"12": "O"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"B-EMAIL": 0,
|
29 |
+
"B-ID_NUM": 1,
|
30 |
+
"B-NAME_STUDENT": 2,
|
31 |
+
"B-PHONE_NUM": 3,
|
32 |
+
"B-STREET_ADDRESS": 4,
|
33 |
+
"B-URL_PERSONAL": 5,
|
34 |
+
"B-USERNAME": 6,
|
35 |
+
"I-ID_NUM": 7,
|
36 |
+
"I-NAME_STUDENT": 8,
|
37 |
+
"I-PHONE_NUM": 9,
|
38 |
+
"I-STREET_ADDRESS": 10,
|
39 |
+
"I-URL_PERSONAL": 11,
|
40 |
+
"O": 12
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-07,
|
43 |
+
"max_position_embeddings": 512,
|
44 |
+
"max_relative_positions": -1,
|
45 |
+
"model_type": "deberta-v2",
|
46 |
+
"norm_rel_ebd": "layer_norm",
|
47 |
+
"num_attention_heads": 16,
|
48 |
+
"num_hidden_layers": 24,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"pooler_dropout": 0,
|
51 |
+
"pooler_hidden_act": "gelu",
|
52 |
+
"pooler_hidden_size": 1024,
|
53 |
+
"pos_att_type": [
|
54 |
+
"p2c",
|
55 |
+
"c2p"
|
56 |
+
],
|
57 |
+
"position_biased_input": false,
|
58 |
+
"position_buckets": 256,
|
59 |
+
"relative_attention": true,
|
60 |
+
"share_att_key": true,
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.38.2",
|
63 |
+
"type_vocab_size": 0,
|
64 |
+
"vocab_size": 128100
|
65 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77de8dcf39c9b1660819676eb1706cfe08a6ebde7984c1ffba182ab04d481f2a
|
3 |
+
size 1736150964
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"split_by_punct": false,
|
55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
56 |
+
"unk_token": "[UNK]",
|
57 |
+
"vocab_type": "spm"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f3aa6808fdebe7ad398cc857e0d26d9d5686fa9e100f388b276eec185c42db6
|
3 |
+
size 4856
|