Pclanglais commited on
Commit
ea3d8c4
1 Parent(s): c527675

Upload folder using huggingface_hub

Browse files
.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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./text-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": "author",
12
+ "1": "bibliography",
13
+ "2": "caption",
14
+ "3": "contact",
15
+ "4": "date",
16
+ "5": "dialog",
17
+ "6": "footnote",
18
+ "7": "keywords",
19
+ "8": "math",
20
+ "9": "paratext",
21
+ "10": "separator",
22
+ "11": "table",
23
+ "12": "text",
24
+ "13": "title"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "author": 0,
30
+ "bibliography": 1,
31
+ "caption": 2,
32
+ "contact": 3,
33
+ "date": 4,
34
+ "dialog": 5,
35
+ "footnote": 6,
36
+ "keywords": 7,
37
+ "math": 8,
38
+ "paratext": 9,
39
+ "separator": 10,
40
+ "table": 11,
41
+ "text": 12,
42
+ "title": 13
43
+ },
44
+ "layer_norm_eps": 1e-07,
45
+ "max_position_embeddings": 512,
46
+ "max_relative_positions": -1,
47
+ "model_type": "deberta-v2",
48
+ "norm_rel_ebd": "layer_norm",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 0,
52
+ "pooler_dropout": 0,
53
+ "pooler_hidden_act": "gelu",
54
+ "pooler_hidden_size": 768,
55
+ "pos_att_type": [
56
+ "p2c",
57
+ "c2p"
58
+ ],
59
+ "position_biased_input": false,
60
+ "position_buckets": 256,
61
+ "relative_attention": true,
62
+ "share_att_key": true,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.41.2",
65
+ "type_vocab_size": 0,
66
+ "vocab_size": 251000
67
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f85b263a5ee0d7733e512355fdef4f418af1d6f082d1bbab66a53a8c291529
3
+ size 1112942568
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:fb7845b8cfdcdf6aaf7bd25a4f748d7982b5deac775a33e553d58fbf6f5730f8
3
+ size 5176