Hugging Face's logo

phonemetransformers
/
childes-segmentation-random-gpt2_lm-model

Text Generation
Transformers
Safetensors
gpt2
Unigram
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
codebyzeb commited on
Commit
bba9867
·
verified ·
1 Parent(s): 73592cf

Training in progress, step 20000

Browse files
Files changed (7) hide show
  1. config.json +31 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer.json +164 -0
  5. tokenizer_config.json +44 -0
  6. training_args.bin +3 -0
  7. vocab.json +1 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.3,
7
+ "bos_token_id": 3,
8
+ "embd_pdrop": 0.3,
9
+ "eos_token_id": 3,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 256,
14
+ "n_head": 8,
15
+ "n_inner": 1024,
16
+ "n_layer": 6,
17
+ "n_positions": 256,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.3,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.44.2",
29
+ "use_cache": true,
30
+ "vocab_size": 47
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835d95400106ec6c8add7f2e9ae1eb4cd160087eaff16d70293ab48bb9279eea
3
+ size 19274048
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "UTT_BOUNDARY",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "UTT_BOUNDARY",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "PAD",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "UNK",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "PAD",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "WORD_BOUNDARY",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "UTT_BOUNDARY",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": {
44
+ "type": "Sequence",
45
+ "normalizers": [
46
+ {
47
+ "type": "Strip",
48
+ "strip_left": true,
49
+ "strip_right": true
50
+ }
51
+ ]
52
+ },
53
+ "pre_tokenizer": {
54
+ "type": "Whitespace"
55
+ },
56
+ "post_processor": {
57
+ "type": "TemplateProcessing",
58
+ "single": [
59
+ {
60
+ "SpecialToken": {
61
+ "id": "UTT_BOUNDARY",
62
+ "type_id": 0
63
+ }
64
+ },
65
+ {
66
+ "Sequence": {
67
+ "id": "A",
68
+ "type_id": 0
69
+ }
70
+ }
71
+ ],
72
+ "pair": [
73
+ {
74
+ "SpecialToken": {
75
+ "id": "UTT_BOUNDARY",
76
+ "type_id": 0
77
+ }
78
+ },
79
+ {
80
+ "Sequence": {
81
+ "id": "A",
82
+ "type_id": 0
83
+ }
84
+ },
85
+ {
86
+ "SpecialToken": {
87
+ "id": "UTT_BOUNDARY",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "Sequence": {
93
+ "id": "B",
94
+ "type_id": 1
95
+ }
96
+ }
97
+ ],
98
+ "special_tokens": {
99
+ "UTT_BOUNDARY": {
100
+ "id": "UTT_BOUNDARY",
101
+ "ids": [
102
+ 3
103
+ ],
104
+ "tokens": [
105
+ "UTT_BOUNDARY"
106
+ ]
107
+ }
108
+ }
109
+ },
110
+ "decoder": null,
111
+ "model": {
112
+ "type": "WordLevel",
113
+ "vocab": {
114
+ "UNK": 0,
115
+ "PAD": 1,
116
+ "WORD_BOUNDARY": 2,
117
+ "UTT_BOUNDARY": 3,
118
+ "d̠ʒ": 4,
119
+ "ʌ": 5,
120
+ "s": 6,
121
+ "t": 7,
122
+ "l": 8,
123
+ "aɪ": 9,
124
+ "k": 10,
125
+ "j": 11,
126
+ "ʊ": 12,
127
+ "ɹ": 13,
128
+ "b": 14,
129
+ "æ": 15,
130
+ "h": 16,
131
+ "oʊ": 17,
132
+ "m": 18,
133
+ "iː": 19,
134
+ "ð": 20,
135
+ "ɛ": 21,
136
+ "z": 22,
137
+ "f": 23,
138
+ "eɪ": 24,
139
+ "w": 25,
140
+ "ɪ": 26,
141
+ "ɡ": 27,
142
+ "ɑ": 28,
143
+ "ə": 29,
144
+ "p": 30,
145
+ "uː": 31,
146
+ "i": 32,
147
+ "θ": 33,
148
+ "ŋ": 34,
149
+ "ɔ": 35,
150
+ "ɔɪ": 36,
151
+ "n": 37,
152
+ "d": 38,
153
+ "aʊ": 39,
154
+ "v": 40,
155
+ "ɜː": 41,
156
+ "t̠ʃ": 42,
157
+ "ʃ": 43,
158
+ "iə": 44,
159
+ "ʒ": 45,
160
+ "x": 46
161
+ },
162
+ "unk_token": "UNK"
163
+ }
164
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "PAD",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "WORD_BOUNDARY",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "UTT_BOUNDARY",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "UTT_BOUNDARY",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "UTT_BOUNDARY",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "PAD",
42
+ "tokenizer_class": "GPT2Tokenizer",
43
+ "unk_token": "UNK"
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3170009284ceb3794083129280d311dae15a280fe7212e783ec65589dd1f78d7
3
+ size 5368
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"d̠ʒ":4,"ʌ":5,"s":6,"t":7,"l":8,"aɪ":9,"k":10,"j":11,"ʊ":12,"ɹ":13,"b":14,"æ":15,"h":16,"oʊ":17,"m":18,"iː":19,"ð":20,"ɛ":21,"z":22,"f":23,"eɪ":24,"w":25,"ɪ":26,"ɡ":27,"ɑ":28,"ə":29,"p":30,"uː":31,"i":32,"θ":33,"ŋ":34,"ɔ":35,"ɔɪ":36,"n":37,"d":38,"aʊ":39,"v":40,"ɜː":41,"t̠ʃ":42,"ʃ":43,"iə":44,"ʒ":45,"x":46}