alxho commited on
Commit
dcb2c52
·
verified ·
1 Parent(s): 1e1affc

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 2,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 3,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 128,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 128,
19
+ "pad_token_id": 0,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.50.1",
31
+ "use_cache": true,
32
+ "vocab_size": 42
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.50.1"
7
+ }
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609599bfee794653b211390790e3c60527ef90b67c96a89c316c8157c7308961
3
+ size 170644936
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[EOS]",
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 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 128
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[UNK]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 2,
40
+ "content": "[BOS]",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 3,
49
+ "content": "[EOS]",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ }
56
+ ],
57
+ "normalizer": null,
58
+ "pre_tokenizer": {
59
+ "type": "Split",
60
+ "pattern": {
61
+ "String": ""
62
+ },
63
+ "behavior": "Isolated",
64
+ "invert": false
65
+ },
66
+ "post_processor": {
67
+ "type": "TemplateProcessing",
68
+ "single": [
69
+ {
70
+ "SpecialToken": {
71
+ "id": "[BOS]",
72
+ "type_id": 0
73
+ }
74
+ },
75
+ {
76
+ "Sequence": {
77
+ "id": "A",
78
+ "type_id": 0
79
+ }
80
+ },
81
+ {
82
+ "SpecialToken": {
83
+ "id": "[EOS]",
84
+ "type_id": 0
85
+ }
86
+ }
87
+ ],
88
+ "pair": [
89
+ {
90
+ "Sequence": {
91
+ "id": "A",
92
+ "type_id": 0
93
+ }
94
+ },
95
+ {
96
+ "Sequence": {
97
+ "id": "B",
98
+ "type_id": 1
99
+ }
100
+ }
101
+ ],
102
+ "special_tokens": {
103
+ "[BOS]": {
104
+ "id": "[BOS]",
105
+ "ids": [
106
+ 2
107
+ ],
108
+ "tokens": [
109
+ "[BOS]"
110
+ ]
111
+ },
112
+ "[EOS]": {
113
+ "id": "[EOS]",
114
+ "ids": [
115
+ 3
116
+ ],
117
+ "tokens": [
118
+ "[EOS]"
119
+ ]
120
+ }
121
+ }
122
+ },
123
+ "decoder": null,
124
+ "model": {
125
+ "type": "BPE",
126
+ "dropout": null,
127
+ "unk_token": "[UNK]",
128
+ "continuing_subword_prefix": null,
129
+ "end_of_word_suffix": null,
130
+ "fuse_unk": false,
131
+ "byte_fallback": false,
132
+ "ignore_merges": false,
133
+ "vocab": {
134
+ "[PAD]": 0,
135
+ "[UNK]": 1,
136
+ "[BOS]": 2,
137
+ "[EOS]": 3,
138
+ "\u0001": 4,
139
+ "#": 5,
140
+ "(": 6,
141
+ ")": 7,
142
+ "+": 8,
143
+ "-": 9,
144
+ "/": 10,
145
+ "1": 11,
146
+ "2": 12,
147
+ "3": 13,
148
+ "4": 14,
149
+ "5": 15,
150
+ "6": 16,
151
+ "7": 17,
152
+ "8": 18,
153
+ "=": 19,
154
+ "@": 20,
155
+ "B": 21,
156
+ "C": 22,
157
+ "F": 23,
158
+ "H": 24,
159
+ "I": 25,
160
+ "N": 26,
161
+ "O": 27,
162
+ "P": 28,
163
+ "S": 29,
164
+ "[": 30,
165
+ "\\": 31,
166
+ "]": 32,
167
+ "c": 33,
168
+ "e": 34,
169
+ "i": 35,
170
+ "l": 36,
171
+ "n": 37,
172
+ "o": 38,
173
+ "p": 39,
174
+ "r": 40,
175
+ "s": 41
176
+ },
177
+ "merges": []
178
+ }
179
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[BOS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[EOS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "[BOS]",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "[EOS]",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "[UNK]"
45
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[PAD]":0,"[UNK]":1,"[BOS]":2,"[EOS]":3,"\u0001":4,"#":5,"(":6,")":7,"+":8,"-":9,"/":10,"1":11,"2":12,"3":13,"4":14,"5":15,"6":16,"7":17,"8":18,"=":19,"@":20,"B":21,"C":22,"F":23,"H":24,"I":25,"N":26,"O":27,"P":28,"S":29,"[":30,"\\":31,"]":32,"c":33,"e":34,"i":35,"l":36,"n":37,"o":38,"p":39,"r":40,"s":41}