leejason2025 commited on
Commit
a160932
·
verified ·
1 Parent(s): 7bbb49f

add 150m-web150m-1b/step_30517

Browse files
150m-web150m-1b/step_30517/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message['content'] }}{% endfor %}
150m-web150m-1b/step_30517/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": null,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": null,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 512,
20
+ "pad_token_id": 275,
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
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.14.1",
32
+ "use_cache": true,
33
+ "vocab_size": 276
34
+ }
150m-web150m-1b/step_30517/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "pad_token_id": 275,
6
+ "transformers_version": "5.14.1",
7
+ "use_cache": true
8
+ }
150m-web150m-1b/step_30517/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e873d3eacea84a850fa057ee035c6c19479fcf361af743346e7b2681c455d1
3
+ size 607869760
150m-web150m-1b/step_30517/tokenizer.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 275,
8
+ "content": "<PAD>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ }
15
+ ],
16
+ "normalizer": null,
17
+ "pre_tokenizer": {
18
+ "type": "WhitespaceSplit"
19
+ },
20
+ "post_processor": {
21
+ "type": "TemplateProcessing",
22
+ "single": [
23
+ {
24
+ "Sequence": {
25
+ "id": "A",
26
+ "type_id": 0
27
+ }
28
+ }
29
+ ],
30
+ "pair": [
31
+ {
32
+ "Sequence": {
33
+ "id": "A",
34
+ "type_id": 0
35
+ }
36
+ },
37
+ {
38
+ "Sequence": {
39
+ "id": "B",
40
+ "type_id": 1
41
+ }
42
+ }
43
+ ],
44
+ "special_tokens": {}
45
+ },
46
+ "decoder": null,
47
+ "model": {
48
+ "type": "WordLevel",
49
+ "vocab": {
50
+ "<BYTE_0>": 0,
51
+ "<BYTE_1>": 1,
52
+ "<BYTE_2>": 2,
53
+ "<BYTE_3>": 3,
54
+ "<BYTE_4>": 4,
55
+ "<BYTE_5>": 5,
56
+ "<BYTE_6>": 6,
57
+ "<BYTE_7>": 7,
58
+ "<BYTE_8>": 8,
59
+ "<BYTE_9>": 9,
60
+ "<BYTE_10>": 10,
61
+ "<BYTE_11>": 11,
62
+ "<BYTE_12>": 12,
63
+ "<BYTE_13>": 13,
64
+ "<BYTE_14>": 14,
65
+ "<BYTE_15>": 15,
66
+ "<BYTE_16>": 16,
67
+ "<BYTE_17>": 17,
68
+ "<BYTE_18>": 18,
69
+ "<BYTE_19>": 19,
70
+ "<BYTE_20>": 20,
71
+ "<BYTE_21>": 21,
72
+ "<BYTE_22>": 22,
73
+ "<BYTE_23>": 23,
74
+ "<BYTE_24>": 24,
75
+ "<BYTE_25>": 25,
76
+ "<BYTE_26>": 26,
77
+ "<BYTE_27>": 27,
78
+ "<BYTE_28>": 28,
79
+ "<BYTE_29>": 29,
80
+ "<BYTE_30>": 30,
81
+ "<BYTE_31>": 31,
82
+ "<BYTE_32>": 32,
83
+ "<BYTE_33>": 33,
84
+ "<BYTE_34>": 34,
85
+ "<BYTE_35>": 35,
86
+ "<BYTE_36>": 36,
87
+ "<BYTE_37>": 37,
88
+ "<BYTE_38>": 38,
89
+ "<BYTE_39>": 39,
90
+ "<BYTE_40>": 40,
91
+ "<BYTE_41>": 41,
92
+ "<BYTE_42>": 42,
93
+ "<BYTE_43>": 43,
94
+ "<BYTE_44>": 44,
95
+ "<BYTE_45>": 45,
96
+ "<BYTE_46>": 46,
97
+ "<BYTE_47>": 47,
98
+ "<BYTE_48>": 48,
99
+ "<BYTE_49>": 49,
100
+ "<BYTE_50>": 50,
101
+ "<BYTE_51>": 51,
102
+ "<BYTE_52>": 52,
103
+ "<BYTE_53>": 53,
104
+ "<BYTE_54>": 54,
105
+ "<BYTE_55>": 55,
106
+ "<BYTE_56>": 56,
107
+ "<BYTE_57>": 57,
108
+ "<BYTE_58>": 58,
109
+ "<BYTE_59>": 59,
110
+ "<BYTE_60>": 60,
111
+ "<BYTE_61>": 61,
112
+ "<BYTE_62>": 62,
113
+ "<BYTE_63>": 63,
114
+ "<BYTE_64>": 64,
115
+ "<BYTE_65>": 65,
116
+ "<BYTE_66>": 66,
117
+ "<BYTE_67>": 67,
118
+ "<BYTE_68>": 68,
119
+ "<BYTE_69>": 69,
120
+ "<BYTE_70>": 70,
121
+ "<BYTE_71>": 71,
122
+ "<BYTE_72>": 72,
123
+ "<BYTE_73>": 73,
124
+ "<BYTE_74>": 74,
125
+ "<BYTE_75>": 75,
126
+ "<BYTE_76>": 76,
127
+ "<BYTE_77>": 77,
128
+ "<BYTE_78>": 78,
129
+ "<BYTE_79>": 79,
130
+ "<BYTE_80>": 80,
131
+ "<BYTE_81>": 81,
132
+ "<BYTE_82>": 82,
133
+ "<BYTE_83>": 83,
134
+ "<BYTE_84>": 84,
135
+ "<BYTE_85>": 85,
136
+ "<BYTE_86>": 86,
137
+ "<BYTE_87>": 87,
138
+ "<BYTE_88>": 88,
139
+ "<BYTE_89>": 89,
140
+ "<BYTE_90>": 90,
141
+ "<BYTE_91>": 91,
142
+ "<BYTE_92>": 92,
143
+ "<BYTE_93>": 93,
144
+ "<BYTE_94>": 94,
145
+ "<BYTE_95>": 95,
146
+ "<BYTE_96>": 96,
147
+ "<BYTE_97>": 97,
148
+ "<BYTE_98>": 98,
149
+ "<BYTE_99>": 99,
150
+ "<BYTE_100>": 100,
151
+ "<BYTE_101>": 101,
152
+ "<BYTE_102>": 102,
153
+ "<BYTE_103>": 103,
154
+ "<BYTE_104>": 104,
155
+ "<BYTE_105>": 105,
156
+ "<BYTE_106>": 106,
157
+ "<BYTE_107>": 107,
158
+ "<BYTE_108>": 108,
159
+ "<BYTE_109>": 109,
160
+ "<BYTE_110>": 110,
161
+ "<BYTE_111>": 111,
162
+ "<BYTE_112>": 112,
163
+ "<BYTE_113>": 113,
164
+ "<BYTE_114>": 114,
165
+ "<BYTE_115>": 115,
166
+ "<BYTE_116>": 116,
167
+ "<BYTE_117>": 117,
168
+ "<BYTE_118>": 118,
169
+ "<BYTE_119>": 119,
170
+ "<BYTE_120>": 120,
171
+ "<BYTE_121>": 121,
172
+ "<BYTE_122>": 122,
173
+ "<BYTE_123>": 123,
174
+ "<BYTE_124>": 124,
175
+ "<BYTE_125>": 125,
176
+ "<BYTE_126>": 126,
177
+ "<BYTE_127>": 127,
178
+ "<BYTE_128>": 128,
179
+ "<BYTE_129>": 129,
180
+ "<BYTE_130>": 130,
181
+ "<BYTE_131>": 131,
182
+ "<BYTE_132>": 132,
183
+ "<BYTE_133>": 133,
184
+ "<BYTE_134>": 134,
185
+ "<BYTE_135>": 135,
186
+ "<BYTE_136>": 136,
187
+ "<BYTE_137>": 137,
188
+ "<BYTE_138>": 138,
189
+ "<BYTE_139>": 139,
190
+ "<BYTE_140>": 140,
191
+ "<BYTE_141>": 141,
192
+ "<BYTE_142>": 142,
193
+ "<BYTE_143>": 143,
194
+ "<BYTE_144>": 144,
195
+ "<BYTE_145>": 145,
196
+ "<BYTE_146>": 146,
197
+ "<BYTE_147>": 147,
198
+ "<BYTE_148>": 148,
199
+ "<BYTE_149>": 149,
200
+ "<BYTE_150>": 150,
201
+ "<BYTE_151>": 151,
202
+ "<BYTE_152>": 152,
203
+ "<BYTE_153>": 153,
204
+ "<BYTE_154>": 154,
205
+ "<BYTE_155>": 155,
206
+ "<BYTE_156>": 156,
207
+ "<BYTE_157>": 157,
208
+ "<BYTE_158>": 158,
209
+ "<BYTE_159>": 159,
210
+ "<BYTE_160>": 160,
211
+ "<BYTE_161>": 161,
212
+ "<BYTE_162>": 162,
213
+ "<BYTE_163>": 163,
214
+ "<BYTE_164>": 164,
215
+ "<BYTE_165>": 165,
216
+ "<BYTE_166>": 166,
217
+ "<BYTE_167>": 167,
218
+ "<BYTE_168>": 168,
219
+ "<BYTE_169>": 169,
220
+ "<BYTE_170>": 170,
221
+ "<BYTE_171>": 171,
222
+ "<BYTE_172>": 172,
223
+ "<BYTE_173>": 173,
224
+ "<BYTE_174>": 174,
225
+ "<BYTE_175>": 175,
226
+ "<BYTE_176>": 176,
227
+ "<BYTE_177>": 177,
228
+ "<BYTE_178>": 178,
229
+ "<BYTE_179>": 179,
230
+ "<BYTE_180>": 180,
231
+ "<BYTE_181>": 181,
232
+ "<BYTE_182>": 182,
233
+ "<BYTE_183>": 183,
234
+ "<BYTE_184>": 184,
235
+ "<BYTE_185>": 185,
236
+ "<BYTE_186>": 186,
237
+ "<BYTE_187>": 187,
238
+ "<BYTE_188>": 188,
239
+ "<BYTE_189>": 189,
240
+ "<BYTE_190>": 190,
241
+ "<BYTE_191>": 191,
242
+ "<BYTE_192>": 192,
243
+ "<BYTE_193>": 193,
244
+ "<BYTE_194>": 194,
245
+ "<BYTE_195>": 195,
246
+ "<BYTE_196>": 196,
247
+ "<BYTE_197>": 197,
248
+ "<BYTE_198>": 198,
249
+ "<BYTE_199>": 199,
250
+ "<BYTE_200>": 200,
251
+ "<BYTE_201>": 201,
252
+ "<BYTE_202>": 202,
253
+ "<BYTE_203>": 203,
254
+ "<BYTE_204>": 204,
255
+ "<BYTE_205>": 205,
256
+ "<BYTE_206>": 206,
257
+ "<BYTE_207>": 207,
258
+ "<BYTE_208>": 208,
259
+ "<BYTE_209>": 209,
260
+ "<BYTE_210>": 210,
261
+ "<BYTE_211>": 211,
262
+ "<BYTE_212>": 212,
263
+ "<BYTE_213>": 213,
264
+ "<BYTE_214>": 214,
265
+ "<BYTE_215>": 215,
266
+ "<BYTE_216>": 216,
267
+ "<BYTE_217>": 217,
268
+ "<BYTE_218>": 218,
269
+ "<BYTE_219>": 219,
270
+ "<BYTE_220>": 220,
271
+ "<BYTE_221>": 221,
272
+ "<BYTE_222>": 222,
273
+ "<BYTE_223>": 223,
274
+ "<BYTE_224>": 224,
275
+ "<BYTE_225>": 225,
276
+ "<BYTE_226>": 226,
277
+ "<BYTE_227>": 227,
278
+ "<BYTE_228>": 228,
279
+ "<BYTE_229>": 229,
280
+ "<BYTE_230>": 230,
281
+ "<BYTE_231>": 231,
282
+ "<BYTE_232>": 232,
283
+ "<BYTE_233>": 233,
284
+ "<BYTE_234>": 234,
285
+ "<BYTE_235>": 235,
286
+ "<BYTE_236>": 236,
287
+ "<BYTE_237>": 237,
288
+ "<BYTE_238>": 238,
289
+ "<BYTE_239>": 239,
290
+ "<BYTE_240>": 240,
291
+ "<BYTE_241>": 241,
292
+ "<BYTE_242>": 242,
293
+ "<BYTE_243>": 243,
294
+ "<BYTE_244>": 244,
295
+ "<BYTE_245>": 245,
296
+ "<BYTE_246>": 246,
297
+ "<BYTE_247>": 247,
298
+ "<BYTE_248>": 248,
299
+ "<BYTE_249>": 249,
300
+ "<BYTE_250>": 250,
301
+ "<BYTE_251>": 251,
302
+ "<BYTE_252>": 252,
303
+ "<BYTE_253>": 253,
304
+ "<BYTE_254>": 254,
305
+ "<BYTE_255>": 255,
306
+ "<DIGIT_0>": 256,
307
+ "<DIGIT_1>": 257,
308
+ "<DIGIT_2>": 258,
309
+ "<DIGIT_3>": 259,
310
+ "<DIGIT_4>": 260,
311
+ "<DIGIT_5>": 261,
312
+ "<DIGIT_6>": 262,
313
+ "<DIGIT_7>": 263,
314
+ "<DIGIT_8>": 264,
315
+ "<DIGIT_9>": 265,
316
+ "<ADD>": 266,
317
+ "<SUB>": 267,
318
+ "<MULTIPLY>": 268,
319
+ "<START>": 269,
320
+ "<STEP>": 270,
321
+ "<FINAL>": 271,
322
+ "<PIPE>": 272,
323
+ "<COLON>": 273,
324
+ "<BOUNDARY>": 274,
325
+ "<PAD>": 275
326
+ },
327
+ "unk_token": "<unk>"
328
+ }
329
+ }
150m-web150m-1b/step_30517/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "is_local": true,
4
+ "local_files_only": false,
5
+ "model_max_length": 1000000000,
6
+ "pad_token": "<PAD>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }