Hugging Face's logo

musiclang
/
musiclang-chord-v2-4k

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
floriangardin commited on
Commit
0123fea
·
verified ·
1 Parent(s): a61cd4a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +129 -0
  3. tokenizer_config.json +80 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[START]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[END]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "[START]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 47,
62
+ "content": "[END]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ }
69
+ ],
70
+ "normalizer": null,
71
+ "pre_tokenizer": {
72
+ "type": "WhitespaceSplit"
73
+ },
74
+ "post_processor": null,
75
+ "decoder": null,
76
+ "model": {
77
+ "type": "WordLevel",
78
+ "vocab": {
79
+ "[UNK]": 0,
80
+ "[CLS]": 1,
81
+ "[SEP]": 2,
82
+ "[PAD]": 3,
83
+ "[MASK]": 4,
84
+ "[START]": 5,
85
+ "CHORD_CHANGE": 6,
86
+ "TONALITY_MODE__M": 7,
87
+ "CHORD_OCTAVE__-1": 8,
88
+ "CHORD_EXTENSION__": 9,
89
+ "CHORD_DEGREE__0": 10,
90
+ "CHORD_DEGREE__4": 11,
91
+ "CHORD_OCTAVE__0": 12,
92
+ "TONALITY_DEGREE__0": 13,
93
+ "CHORD_EXTENSION__64": 14,
94
+ "TONALITY_MODE__m": 15,
95
+ "TONALITY_DEGREE__7": 16,
96
+ "CHORD_DEGREE__3": 17,
97
+ "CHORD_DEGREE__1": 18,
98
+ "TONALITY_DEGREE__9": 19,
99
+ "TONALITY_DEGREE__5": 20,
100
+ "TONALITY_DEGREE__2": 21,
101
+ "CHORD_OCTAVE__-2": 22,
102
+ "CHORD_DEGREE__5": 23,
103
+ "TONALITY_DEGREE__4": 24,
104
+ "TONALITY_DEGREE__10": 25,
105
+ "TONALITY_DEGREE__3": 26,
106
+ "CHORD_EXTENSION__7": 27,
107
+ "CHORD_EXTENSION__6": 28,
108
+ "CHORD_DEGREE__2": 29,
109
+ "TONALITY_DEGREE__8": 30,
110
+ "TONALITY_DEGREE__1": 31,
111
+ "TONALITY_DEGREE__11": 32,
112
+ "TONALITY_DEGREE__6": 33,
113
+ "CHORD_EXTENSION__2": 34,
114
+ "CHORD_EXTENSION__43": 35,
115
+ "CHORD_EXTENSION__6(sus4)": 36,
116
+ "CHORD_EXTENSION__(sus4)": 37,
117
+ "CHORD_EXTENSION__(sus2)": 38,
118
+ "CHORD_DEGREE__6": 39,
119
+ "END": 40,
120
+ "CHORD_EXTENSION__64(sus2)": 41,
121
+ "CHORD_EXTENSION__65": 42,
122
+ "CHORD_EXTENSION__64(sus4)": 43,
123
+ "CHORD_EXTENSION__6(sus2)": 44,
124
+ "CHORD_OCTAVE__-3": 45,
125
+ "CHORD_EXTENSION__(+)": 46
126
+ },
127
+ "unk_token": "[UNK]"
128
+ }
129
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[UNK]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[PAD]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "[START]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "47": {
53
+ "content": "[END]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "bos_token": "[START]",
62
+ "bos_token_id": 5,
63
+ "clean_up_tokenization_spaces": true,
64
+ "cls_token": "[CLS]",
65
+ "cls_token_id": 1,
66
+ "eos_token": "[END]",
67
+ "eos_token_id": 47,
68
+ "mask_token": "[MASK]",
69
+ "mask_token_id": 4,
70
+ "model_max_len": 4096,
71
+ "model_max_length": 4096,
72
+ "pad_token": "[PAD]",
73
+ "pad_token_id": 3,
74
+ "seo_token_id": 2,
75
+ "sep_token": "[SEP]",
76
+ "tokenizer_class": "PreTrainedTokenizerFast",
77
+ "type": "Split",
78
+ "unk_token": "[UNK]",
79
+ "unk_token_id": 0
80
+ }