Hugging Face's logo

DataAnalyticsLab
/
SymbolicGPT-1Vars-30Points-1Ys

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
vpcom commited on
Commit
a6c5a27
·
1 Parent(s): 9a0245e

Training in progress, step 100

Browse files
Files changed (7) hide show
  1. config.json +34 -0
  2. merges.txt +24 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer_config.json +46 -0
  6. training_args.bin +3 -0
  7. vocab.json +286 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "SymbolicGPTLMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 512,
14
+ "n_head": 8,
15
+ "n_inner": null,
16
+ "n_layer": 8,
17
+ "n_points": 30,
18
+ "n_positions": 256,
19
+ "n_vars": 1,
20
+ "n_ys": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.35.0",
32
+ "use_cache": true,
33
+ "vocab_size": 284
34
+ }
merges.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #version: 0.2
2
+ ) +
3
+ * *
4
+ e x
5
+ ex p
6
+ i n
7
+ s in
8
+ c o
9
+ co s
10
+ l o
11
+ lo g
12
+ ) )+
13
+ / (
14
+ ) *
15
+ ) **
16
+ ) /
17
+ ) ))+
18
+ ) /(
19
+ ) )*
20
+ C e
21
+ ) )**
22
+ ) )/
23
+ ) )/(
24
+ ** (
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4af08afa1baa9e76dc0c803fcb6932abcea11d1953cd45c96fce4e3d644694
3
+ size 123078536
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|EOS|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|UNK|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|BOS|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|PAD|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|EOS|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|UNK|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<|BOS|>",
39
+ "clean_up_tokenization_spaces": true,
40
+ "eos_token": "<|EOS|>",
41
+ "errors": "replace",
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<|PAD|>",
44
+ "tokenizer_class": "SymbolicGPTTokenizer",
45
+ "unk_token": "<|UNK|>"
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8203eb8326056e4278517a9b35c6cb458f5af2d93e6dc5d4d8582940f40d3e0b
3
+ size 4283
vocab.json ADDED
@@ -0,0 +1,286 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 5,
3
+ "\"": 6,
4
+ "#": 7,
5
+ "$": 8,
6
+ "%": 9,
7
+ "&": 10,
8
+ "'": 11,
9
+ "(": 12,
10
+ ")": 13,
11
+ ")))+": 276,
12
+ "))*": 278,
13
+ "))**": 280,
14
+ "))+": 271,
15
+ "))/": 281,
16
+ "))/(": 282,
17
+ ")*": 273,
18
+ ")**": 274,
19
+ ")+": 261,
20
+ ")/": 275,
21
+ ")/(": 277,
22
+ "*": 14,
23
+ "**": 262,
24
+ "**(": 283,
25
+ "+": 15,
26
+ ",": 16,
27
+ "-": 17,
28
+ ".": 18,
29
+ "/": 19,
30
+ "/(": 272,
31
+ "0": 20,
32
+ "1": 21,
33
+ "2": 22,
34
+ "3": 23,
35
+ "4": 24,
36
+ "5": 25,
37
+ "6": 26,
38
+ "7": 27,
39
+ "8": 28,
40
+ "9": 29,
41
+ ":": 30,
42
+ ";": 31,
43
+ "<": 32,
44
+ "<|BOS|>": 0,
45
+ "<|EOS|>": 2,
46
+ "<|MASK|>": 4,
47
+ "<|PAD|>": 1,
48
+ "<|UNK|>": 3,
49
+ "=": 33,
50
+ ">": 34,
51
+ "?": 35,
52
+ "@": 36,
53
+ "A": 37,
54
+ "B": 38,
55
+ "C": 39,
56
+ "Ce": 279,
57
+ "D": 40,
58
+ "E": 41,
59
+ "F": 42,
60
+ "G": 43,
61
+ "H": 44,
62
+ "I": 45,
63
+ "J": 46,
64
+ "K": 47,
65
+ "L": 48,
66
+ "M": 49,
67
+ "N": 50,
68
+ "O": 51,
69
+ "P": 52,
70
+ "Q": 53,
71
+ "R": 54,
72
+ "S": 55,
73
+ "T": 56,
74
+ "U": 57,
75
+ "V": 58,
76
+ "W": 59,
77
+ "X": 60,
78
+ "Y": 61,
79
+ "Z": 62,
80
+ "[": 63,
81
+ "\\": 64,
82
+ "]": 65,
83
+ "^": 66,
84
+ "_": 67,
85
+ "`": 68,
86
+ "a": 69,
87
+ "b": 70,
88
+ "c": 71,
89
+ "co": 267,
90
+ "cos": 268,
91
+ "d": 72,
92
+ "e": 73,
93
+ "ex": 263,
94
+ "exp": 264,
95
+ "f": 74,
96
+ "g": 75,
97
+ "h": 76,
98
+ "i": 77,
99
+ "in": 265,
100
+ "j": 78,
101
+ "k": 79,
102
+ "l": 80,
103
+ "lo": 269,
104
+ "log": 270,
105
+ "m": 81,
106
+ "n": 82,
107
+ "o": 83,
108
+ "p": 84,
109
+ "q": 85,
110
+ "r": 86,
111
+ "s": 87,
112
+ "sin": 266,
113
+ "t": 88,
114
+ "u": 89,
115
+ "v": 90,
116
+ "w": 91,
117
+ "x": 92,
118
+ "y": 93,
119
+ "z": 94,
120
+ "{": 95,
121
+ "|": 96,
122
+ "}": 97,
123
+ "~": 98,
124
+ "¡": 99,
125
+ "¢": 100,
126
+ "£": 101,
127
+ "¤": 102,
128
+ "¥": 103,
129
+ "¦": 104,
130
+ "§": 105,
131
+ "¨": 106,
132
+ "©": 107,
133
+ "ª": 108,
134
+ "«": 109,
135
+ "¬": 110,
136
+ "®": 111,
137
+ "¯": 112,
138
+ "°": 113,
139
+ "±": 114,
140
+ "²": 115,
141
+ "³": 116,
142
+ "´": 117,
143
+ "µ": 118,
144
+ "¶": 119,
145
+ "·": 120,
146
+ "¸": 121,
147
+ "¹": 122,
148
+ "º": 123,
149
+ "»": 124,
150
+ "¼": 125,
151
+ "½": 126,
152
+ "¾": 127,
153
+ "¿": 128,
154
+ "À": 129,
155
+ "Á": 130,
156
+ "Â": 131,
157
+ "Ã": 132,
158
+ "Ä": 133,
159
+ "Å": 134,
160
+ "Æ": 135,
161
+ "Ç": 136,
162
+ "È": 137,
163
+ "É": 138,
164
+ "Ê": 139,
165
+ "Ë": 140,
166
+ "Ì": 141,
167
+ "Í": 142,
168
+ "Î": 143,
169
+ "Ï": 144,
170
+ "Ð": 145,
171
+ "Ñ": 146,
172
+ "Ò": 147,
173
+ "Ó": 148,
174
+ "Ô": 149,
175
+ "Õ": 150,
176
+ "Ö": 151,
177
+ "×": 152,
178
+ "Ø": 153,
179
+ "Ù": 154,
180
+ "Ú": 155,
181
+ "Û": 156,
182
+ "Ü": 157,
183
+ "Ý": 158,
184
+ "Þ": 159,
185
+ "ß": 160,
186
+ "à": 161,
187
+ "á": 162,
188
+ "â": 163,
189
+ "ã": 164,
190
+ "ä": 165,
191
+ "å": 166,
192
+ "æ": 167,
193
+ "ç": 168,
194
+ "è": 169,
195
+ "é": 170,
196
+ "ê": 171,
197
+ "ë": 172,
198
+ "ì": 173,
199
+ "í": 174,
200
+ "î": 175,
201
+ "ï": 176,
202
+ "ð": 177,
203
+ "ñ": 178,
204
+ "ò": 179,
205
+ "ó": 180,
206
+ "ô": 181,
207
+ "õ": 182,
208
+ "ö": 183,
209
+ "÷": 184,
210
+ "ø": 185,
211
+ "ù": 186,
212
+ "ú": 187,
213
+ "û": 188,
214
+ "ü": 189,
215
+ "ý": 190,
216
+ "þ": 191,
217
+ "ÿ": 192,
218
+ "Ā": 193,
219
+ "ā": 194,
220
+ "Ă": 195,
221
+ "ă": 196,
222
+ "Ą": 197,
223
+ "ą": 198,
224
+ "Ć": 199,
225
+ "ć": 200,
226
+ "Ĉ": 201,
227
+ "ĉ": 202,
228
+ "Ċ": 203,
229
+ "ċ": 204,
230
+ "Č": 205,
231
+ "č": 206,
232
+ "Ď": 207,
233
+ "ď": 208,
234
+ "Đ": 209,
235
+ "đ": 210,
236
+ "Ē": 211,
237
+ "ē": 212,
238
+ "Ĕ": 213,
239
+ "ĕ": 214,
240
+ "Ė": 215,
241
+ "ė": 216,
242
+ "Ę": 217,
243
+ "ę": 218,
244
+ "Ě": 219,
245
+ "ě": 220,
246
+ "Ĝ": 221,
247
+ "ĝ": 222,
248
+ "Ğ": 223,
249
+ "ğ": 224,
250
+ "Ġ": 225,
251
+ "ġ": 226,
252
+ "Ģ": 227,
253
+ "ģ": 228,
254
+ "Ĥ": 229,
255
+ "ĥ": 230,
256
+ "Ħ": 231,
257
+ "ħ": 232,
258
+ "Ĩ": 233,
259
+ "ĩ": 234,
260
+ "Ī": 235,
261
+ "ī": 236,
262
+ "Ĭ": 237,
263
+ "ĭ": 238,
264
+ "Į": 239,
265
+ "į": 240,
266
+ "İ": 241,
267
+ "ı": 242,
268
+ "IJ": 243,
269
+ "ij": 244,
270
+ "Ĵ": 245,
271
+ "ĵ": 246,
272
+ "Ķ": 247,
273
+ "ķ": 248,
274
+ "ĸ": 249,
275
+ "Ĺ": 250,
276
+ "ĺ": 251,
277
+ "Ļ": 252,
278
+ "ļ": 253,
279
+ "Ľ": 254,
280
+ "ľ": 255,
281
+ "Ŀ": 256,
282
+ "ŀ": 257,
283
+ "Ł": 258,
284
+ "ł": 259,
285
+ "Ń": 260
286
+ }