Hugging Face's logo

SaladTechnologies
/
fable-base

Token Classification
Safetensors
English
deberta-v2
Model card Files
xet
Community
shawnrushefsky commited on
Commit
1727f57
·
1 Parent(s): a9f0fc3

Training in progress, step 2300

Browse files
Files changed (5) hide show
  1. added_tokens.json +3 -0
  2. config.json +69 -0
  3. special_tokens_map.json +15 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +59 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "O",
11
+ "1": "B-CHA",
12
+ "2": "I-CHA",
13
+ "3": "B-LOC",
14
+ "4": "I-LOC",
15
+ "5": "B-FAC",
16
+ "6": "I-FAC",
17
+ "7": "B-OBJ",
18
+ "8": "I-OBJ",
19
+ "9": "B-EVT",
20
+ "10": "I-EVT",
21
+ "11": "B-ORG",
22
+ "12": "I-ORG",
23
+ "13": "B-MISC",
24
+ "14": "I-MISC"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "B-CHA": 1,
30
+ "B-EVT": 9,
31
+ "B-FAC": 5,
32
+ "B-LOC": 3,
33
+ "B-MISC": 13,
34
+ "B-OBJ": 7,
35
+ "B-ORG": 11,
36
+ "I-CHA": 2,
37
+ "I-EVT": 10,
38
+ "I-FAC": 6,
39
+ "I-LOC": 4,
40
+ "I-MISC": 14,
41
+ "I-OBJ": 8,
42
+ "I-ORG": 12,
43
+ "O": 0
44
+ },
45
+ "layer_norm_eps": 1e-07,
46
+ "legacy": true,
47
+ "max_position_embeddings": 512,
48
+ "max_relative_positions": -1,
49
+ "model_type": "deberta-v2",
50
+ "norm_rel_ebd": "layer_norm",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "pooler_dropout": 0,
55
+ "pooler_hidden_act": "gelu",
56
+ "pooler_hidden_size": 768,
57
+ "pos_att_type": [
58
+ "p2c",
59
+ "c2p"
60
+ ],
61
+ "position_biased_input": false,
62
+ "position_buckets": 256,
63
+ "relative_attention": true,
64
+ "share_att_key": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.55.4",
67
+ "type_vocab_size": 0,
68
+ "vocab_size": 128100
69
+ }
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }