Pclanglais
commited on
Commit
•
99251c7
1
Parent(s):
3cbb9c2
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- config.json +83 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +58 -0
- training_args.bin +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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 250101
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./bibliography-segmentation",
|
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": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "abstract",
|
12 |
+
"1": "address",
|
13 |
+
"2": "author",
|
14 |
+
"3": "booktitle",
|
15 |
+
"4": "doi",
|
16 |
+
"5": "editor",
|
17 |
+
"6": "file",
|
18 |
+
"7": "issue",
|
19 |
+
"8": "journal",
|
20 |
+
"9": "keywords",
|
21 |
+
"10": "location",
|
22 |
+
"11": "month",
|
23 |
+
"12": "none",
|
24 |
+
"13": "note",
|
25 |
+
"14": "number",
|
26 |
+
"15": "pages",
|
27 |
+
"16": "publisher",
|
28 |
+
"17": "series",
|
29 |
+
"18": "title",
|
30 |
+
"19": "url",
|
31 |
+
"20": "volume",
|
32 |
+
"21": "year"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"abstract": 0,
|
38 |
+
"address": 1,
|
39 |
+
"author": 2,
|
40 |
+
"booktitle": 3,
|
41 |
+
"doi": 4,
|
42 |
+
"editor": 5,
|
43 |
+
"file": 6,
|
44 |
+
"issue": 7,
|
45 |
+
"journal": 8,
|
46 |
+
"keywords": 9,
|
47 |
+
"location": 10,
|
48 |
+
"month": 11,
|
49 |
+
"none": 12,
|
50 |
+
"note": 13,
|
51 |
+
"number": 14,
|
52 |
+
"pages": 15,
|
53 |
+
"publisher": 16,
|
54 |
+
"series": 17,
|
55 |
+
"title": 18,
|
56 |
+
"url": 19,
|
57 |
+
"volume": 20,
|
58 |
+
"year": 21
|
59 |
+
},
|
60 |
+
"layer_norm_eps": 1e-07,
|
61 |
+
"max_position_embeddings": 512,
|
62 |
+
"max_relative_positions": -1,
|
63 |
+
"model_type": "deberta-v2",
|
64 |
+
"norm_rel_ebd": "layer_norm",
|
65 |
+
"num_attention_heads": 12,
|
66 |
+
"num_hidden_layers": 12,
|
67 |
+
"pad_token_id": 0,
|
68 |
+
"pooler_dropout": 0,
|
69 |
+
"pooler_hidden_act": "gelu",
|
70 |
+
"pooler_hidden_size": 768,
|
71 |
+
"pos_att_type": [
|
72 |
+
"p2c",
|
73 |
+
"c2p"
|
74 |
+
],
|
75 |
+
"position_biased_input": false,
|
76 |
+
"position_buckets": 256,
|
77 |
+
"relative_attention": true,
|
78 |
+
"share_att_key": true,
|
79 |
+
"torch_dtype": "float32",
|
80 |
+
"transformers_version": "4.41.2",
|
81 |
+
"type_vocab_size": 0,
|
82 |
+
"vocab_size": 251000
|
83 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a79a87f4f6a9a582974b98a2de1f2474f981de64881b8a9e93207ac9939737c3
|
3 |
+
size 1112967176
|
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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e26ec8cd2234df8edcc6e8c207b66b3162360f9fdc46ee4526a440d0d9d0bb9
|
3 |
+
size 16331374
|
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 |
+
"250101": {
|
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 sha256:1cfe4560ded2473d95d78b6ea5e885c003b620c8ebbcd9a7d5227ed6c837d721
|
3 |
+
size 5176
|