theguywhosucks commited on
Commit
f51a3a1
·
verified ·
1 Parent(s): f67c91e

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 128,
15
+ "n_embd": 512,
16
+ "n_head": 8,
17
+ "n_inner": null,
18
+ "n_layer": 8,
19
+ "n_positions": 128,
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
+ "transformers_version": "4.56.1",
30
+ "use_cache": true,
31
+ "vocab_size": 43
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.56.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742ce8964524d733ab2ce90ab7f45191b119b263d8b9a37223fb59cfb8321c10
3
+ size 101240552
tokenizer.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 43,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 44,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 45,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 46,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Whitespace"
46
+ },
47
+ "post_processor": {
48
+ "type": "TemplateProcessing",
49
+ "single": [
50
+ {
51
+ "SpecialToken": {
52
+ "id": "<bos>",
53
+ "type_id": 0
54
+ }
55
+ },
56
+ {
57
+ "Sequence": {
58
+ "id": "A",
59
+ "type_id": 0
60
+ }
61
+ },
62
+ {
63
+ "SpecialToken": {
64
+ "id": "<eos>",
65
+ "type_id": 0
66
+ }
67
+ }
68
+ ],
69
+ "pair": [
70
+ {
71
+ "SpecialToken": {
72
+ "id": "<bos>",
73
+ "type_id": 0
74
+ }
75
+ },
76
+ {
77
+ "Sequence": {
78
+ "id": "A",
79
+ "type_id": 0
80
+ }
81
+ },
82
+ {
83
+ "SpecialToken": {
84
+ "id": "<eos>",
85
+ "type_id": 0
86
+ }
87
+ },
88
+ {
89
+ "Sequence": {
90
+ "id": "B",
91
+ "type_id": 1
92
+ }
93
+ },
94
+ {
95
+ "SpecialToken": {
96
+ "id": "<eos>",
97
+ "type_id": 1
98
+ }
99
+ }
100
+ ],
101
+ "special_tokens": {
102
+ "<bos>": {
103
+ "id": "<bos>",
104
+ "ids": [
105
+ 43
106
+ ],
107
+ "tokens": [
108
+ "<bos>"
109
+ ]
110
+ },
111
+ "<eos>": {
112
+ "id": "<eos>",
113
+ "ids": [
114
+ 44
115
+ ],
116
+ "tokens": [
117
+ "<eos>"
118
+ ]
119
+ }
120
+ }
121
+ },
122
+ "decoder": null,
123
+ "model": {
124
+ "type": "WordLevel",
125
+ "vocab": {
126
+ " ": 0,
127
+ "!": 1,
128
+ "'": 2,
129
+ ",": 3,
130
+ "-": 4,
131
+ ".": 5,
132
+ "5": 6,
133
+ "?": 7,
134
+ "A": 8,
135
+ "F": 9,
136
+ "I": 10,
137
+ "M": 11,
138
+ "T": 12,
139
+ "a": 13,
140
+ "b": 14,
141
+ "c": 15,
142
+ "d": 16,
143
+ "e": 17,
144
+ "f": 18,
145
+ "g": 19,
146
+ "h": 20,
147
+ "i": 21,
148
+ "j": 22,
149
+ "k": 23,
150
+ "l": 24,
151
+ "m": 25,
152
+ "n": 26,
153
+ "o": 27,
154
+ "p": 28,
155
+ "q": 29,
156
+ "r": 30,
157
+ "s": 31,
158
+ "t": 32,
159
+ "u": 33,
160
+ "v": 34,
161
+ "w": 35,
162
+ "x": 36,
163
+ "y": 37,
164
+ "z": 38,
165
+ "’": 39,
166
+ "“": 40,
167
+ "”": 41,
168
+ "…": 42
169
+ },
170
+ "unk_token": "<unk>"
171
+ }
172
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast",
3
+ "unk_token": "<unk>",
4
+ "bos_token": "<bos>",
5
+ "eos_token": "<eos>",
6
+ "pad_token": "<pad>"
7
+ }