leejason2025 commited on
Commit
faed954
·
verified ·
1 Parent(s): 196ba74

add 150m-P150s-b15312-m0.5/step_1600

Browse files
150m-P150s-b15312-m0.5/step_1600/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message['content'] }}{% endfor %}
150m-P150s-b15312-m0.5/step_1600/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": "5.15.1",
32
+ "use_cache": true,
33
+ "vocab_size": 276
34
+ }
150m-P150s-b15312-m0.5/step_1600/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": "5.15.1",
7
+ "use_cache": true
8
+ }
150m-P150s-b15312-m0.5/step_1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac2434e9e994f907ecba139e2e5a1bed1ec9207dbd8d8b641da8e224dcad42b
3
+ size 607869760
150m-P150s-b15312-m0.5/step_1600/tokenizer.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": {
5
+ "strategy": "BatchLongest",
6
+ "direction": "Left",
7
+ "pad_to_multiple_of": null,
8
+ "pad_id": 275,
9
+ "pad_type_id": 0,
10
+ "pad_token": "<PAD>"
11
+ },
12
+ "added_tokens": [
13
+ {
14
+ "id": 275,
15
+ "content": "<PAD>",
16
+ "single_word": false,
17
+ "lstrip": false,
18
+ "rstrip": false,
19
+ "normalized": false,
20
+ "special": true
21
+ }
22
+ ],
23
+ "normalizer": null,
24
+ "pre_tokenizer": {
25
+ "type": "WhitespaceSplit"
26
+ },
27
+ "post_processor": {
28
+ "type": "TemplateProcessing",
29
+ "single": [
30
+ {
31
+ "Sequence": {
32
+ "id": "A",
33
+ "type_id": 0
34
+ }
35
+ }
36
+ ],
37
+ "pair": [
38
+ {
39
+ "Sequence": {
40
+ "id": "A",
41
+ "type_id": 0
42
+ }
43
+ },
44
+ {
45
+ "Sequence": {
46
+ "id": "B",
47
+ "type_id": 1
48
+ }
49
+ }
50
+ ],
51
+ "special_tokens": {}
52
+ },
53
+ "decoder": null,
54
+ "model": {
55
+ "type": "WordLevel",
56
+ "vocab": {
57
+ "<BYTE_0>": 0,
58
+ "<BYTE_1>": 1,
59
+ "<BYTE_2>": 2,
60
+ "<BYTE_3>": 3,
61
+ "<BYTE_4>": 4,
62
+ "<BYTE_5>": 5,
63
+ "<BYTE_6>": 6,
64
+ "<BYTE_7>": 7,
65
+ "<BYTE_8>": 8,
66
+ "<BYTE_9>": 9,
67
+ "<BYTE_10>": 10,
68
+ "<BYTE_11>": 11,
69
+ "<BYTE_12>": 12,
70
+ "<BYTE_13>": 13,
71
+ "<BYTE_14>": 14,
72
+ "<BYTE_15>": 15,
73
+ "<BYTE_16>": 16,
74
+ "<BYTE_17>": 17,
75
+ "<BYTE_18>": 18,
76
+ "<BYTE_19>": 19,
77
+ "<BYTE_20>": 20,
78
+ "<BYTE_21>": 21,
79
+ "<BYTE_22>": 22,
80
+ "<BYTE_23>": 23,
81
+ "<BYTE_24>": 24,
82
+ "<BYTE_25>": 25,
83
+ "<BYTE_26>": 26,
84
+ "<BYTE_27>": 27,
85
+ "<BYTE_28>": 28,
86
+ "<BYTE_29>": 29,
87
+ "<BYTE_30>": 30,
88
+ "<BYTE_31>": 31,
89
+ "<BYTE_32>": 32,
90
+ "<BYTE_33>": 33,
91
+ "<BYTE_34>": 34,
92
+ "<BYTE_35>": 35,
93
+ "<BYTE_36>": 36,
94
+ "<BYTE_37>": 37,
95
+ "<BYTE_38>": 38,
96
+ "<BYTE_39>": 39,
97
+ "<BYTE_40>": 40,
98
+ "<BYTE_41>": 41,
99
+ "<BYTE_42>": 42,
100
+ "<BYTE_43>": 43,
101
+ "<BYTE_44>": 44,
102
+ "<BYTE_45>": 45,
103
+ "<BYTE_46>": 46,
104
+ "<BYTE_47>": 47,
105
+ "<BYTE_48>": 48,
106
+ "<BYTE_49>": 49,
107
+ "<BYTE_50>": 50,
108
+ "<BYTE_51>": 51,
109
+ "<BYTE_52>": 52,
110
+ "<BYTE_53>": 53,
111
+ "<BYTE_54>": 54,
112
+ "<BYTE_55>": 55,
113
+ "<BYTE_56>": 56,
114
+ "<BYTE_57>": 57,
115
+ "<BYTE_58>": 58,
116
+ "<BYTE_59>": 59,
117
+ "<BYTE_60>": 60,
118
+ "<BYTE_61>": 61,
119
+ "<BYTE_62>": 62,
120
+ "<BYTE_63>": 63,
121
+ "<BYTE_64>": 64,
122
+ "<BYTE_65>": 65,
123
+ "<BYTE_66>": 66,
124
+ "<BYTE_67>": 67,
125
+ "<BYTE_68>": 68,
126
+ "<BYTE_69>": 69,
127
+ "<BYTE_70>": 70,
128
+ "<BYTE_71>": 71,
129
+ "<BYTE_72>": 72,
130
+ "<BYTE_73>": 73,
131
+ "<BYTE_74>": 74,
132
+ "<BYTE_75>": 75,
133
+ "<BYTE_76>": 76,
134
+ "<BYTE_77>": 77,
135
+ "<BYTE_78>": 78,
136
+ "<BYTE_79>": 79,
137
+ "<BYTE_80>": 80,
138
+ "<BYTE_81>": 81,
139
+ "<BYTE_82>": 82,
140
+ "<BYTE_83>": 83,
141
+ "<BYTE_84>": 84,
142
+ "<BYTE_85>": 85,
143
+ "<BYTE_86>": 86,
144
+ "<BYTE_87>": 87,
145
+ "<BYTE_88>": 88,
146
+ "<BYTE_89>": 89,
147
+ "<BYTE_90>": 90,
148
+ "<BYTE_91>": 91,
149
+ "<BYTE_92>": 92,
150
+ "<BYTE_93>": 93,
151
+ "<BYTE_94>": 94,
152
+ "<BYTE_95>": 95,
153
+ "<BYTE_96>": 96,
154
+ "<BYTE_97>": 97,
155
+ "<BYTE_98>": 98,
156
+ "<BYTE_99>": 99,
157
+ "<BYTE_100>": 100,
158
+ "<BYTE_101>": 101,
159
+ "<BYTE_102>": 102,
160
+ "<BYTE_103>": 103,
161
+ "<BYTE_104>": 104,
162
+ "<BYTE_105>": 105,
163
+ "<BYTE_106>": 106,
164
+ "<BYTE_107>": 107,
165
+ "<BYTE_108>": 108,
166
+ "<BYTE_109>": 109,
167
+ "<BYTE_110>": 110,
168
+ "<BYTE_111>": 111,
169
+ "<BYTE_112>": 112,
170
+ "<BYTE_113>": 113,
171
+ "<BYTE_114>": 114,
172
+ "<BYTE_115>": 115,
173
+ "<BYTE_116>": 116,
174
+ "<BYTE_117>": 117,
175
+ "<BYTE_118>": 118,
176
+ "<BYTE_119>": 119,
177
+ "<BYTE_120>": 120,
178
+ "<BYTE_121>": 121,
179
+ "<BYTE_122>": 122,
180
+ "<BYTE_123>": 123,
181
+ "<BYTE_124>": 124,
182
+ "<BYTE_125>": 125,
183
+ "<BYTE_126>": 126,
184
+ "<BYTE_127>": 127,
185
+ "<BYTE_128>": 128,
186
+ "<BYTE_129>": 129,
187
+ "<BYTE_130>": 130,
188
+ "<BYTE_131>": 131,
189
+ "<BYTE_132>": 132,
190
+ "<BYTE_133>": 133,
191
+ "<BYTE_134>": 134,
192
+ "<BYTE_135>": 135,
193
+ "<BYTE_136>": 136,
194
+ "<BYTE_137>": 137,
195
+ "<BYTE_138>": 138,
196
+ "<BYTE_139>": 139,
197
+ "<BYTE_140>": 140,
198
+ "<BYTE_141>": 141,
199
+ "<BYTE_142>": 142,
200
+ "<BYTE_143>": 143,
201
+ "<BYTE_144>": 144,
202
+ "<BYTE_145>": 145,
203
+ "<BYTE_146>": 146,
204
+ "<BYTE_147>": 147,
205
+ "<BYTE_148>": 148,
206
+ "<BYTE_149>": 149,
207
+ "<BYTE_150>": 150,
208
+ "<BYTE_151>": 151,
209
+ "<BYTE_152>": 152,
210
+ "<BYTE_153>": 153,
211
+ "<BYTE_154>": 154,
212
+ "<BYTE_155>": 155,
213
+ "<BYTE_156>": 156,
214
+ "<BYTE_157>": 157,
215
+ "<BYTE_158>": 158,
216
+ "<BYTE_159>": 159,
217
+ "<BYTE_160>": 160,
218
+ "<BYTE_161>": 161,
219
+ "<BYTE_162>": 162,
220
+ "<BYTE_163>": 163,
221
+ "<BYTE_164>": 164,
222
+ "<BYTE_165>": 165,
223
+ "<BYTE_166>": 166,
224
+ "<BYTE_167>": 167,
225
+ "<BYTE_168>": 168,
226
+ "<BYTE_169>": 169,
227
+ "<BYTE_170>": 170,
228
+ "<BYTE_171>": 171,
229
+ "<BYTE_172>": 172,
230
+ "<BYTE_173>": 173,
231
+ "<BYTE_174>": 174,
232
+ "<BYTE_175>": 175,
233
+ "<BYTE_176>": 176,
234
+ "<BYTE_177>": 177,
235
+ "<BYTE_178>": 178,
236
+ "<BYTE_179>": 179,
237
+ "<BYTE_180>": 180,
238
+ "<BYTE_181>": 181,
239
+ "<BYTE_182>": 182,
240
+ "<BYTE_183>": 183,
241
+ "<BYTE_184>": 184,
242
+ "<BYTE_185>": 185,
243
+ "<BYTE_186>": 186,
244
+ "<BYTE_187>": 187,
245
+ "<BYTE_188>": 188,
246
+ "<BYTE_189>": 189,
247
+ "<BYTE_190>": 190,
248
+ "<BYTE_191>": 191,
249
+ "<BYTE_192>": 192,
250
+ "<BYTE_193>": 193,
251
+ "<BYTE_194>": 194,
252
+ "<BYTE_195>": 195,
253
+ "<BYTE_196>": 196,
254
+ "<BYTE_197>": 197,
255
+ "<BYTE_198>": 198,
256
+ "<BYTE_199>": 199,
257
+ "<BYTE_200>": 200,
258
+ "<BYTE_201>": 201,
259
+ "<BYTE_202>": 202,
260
+ "<BYTE_203>": 203,
261
+ "<BYTE_204>": 204,
262
+ "<BYTE_205>": 205,
263
+ "<BYTE_206>": 206,
264
+ "<BYTE_207>": 207,
265
+ "<BYTE_208>": 208,
266
+ "<BYTE_209>": 209,
267
+ "<BYTE_210>": 210,
268
+ "<BYTE_211>": 211,
269
+ "<BYTE_212>": 212,
270
+ "<BYTE_213>": 213,
271
+ "<BYTE_214>": 214,
272
+ "<BYTE_215>": 215,
273
+ "<BYTE_216>": 216,
274
+ "<BYTE_217>": 217,
275
+ "<BYTE_218>": 218,
276
+ "<BYTE_219>": 219,
277
+ "<BYTE_220>": 220,
278
+ "<BYTE_221>": 221,
279
+ "<BYTE_222>": 222,
280
+ "<BYTE_223>": 223,
281
+ "<BYTE_224>": 224,
282
+ "<BYTE_225>": 225,
283
+ "<BYTE_226>": 226,
284
+ "<BYTE_227>": 227,
285
+ "<BYTE_228>": 228,
286
+ "<BYTE_229>": 229,
287
+ "<BYTE_230>": 230,
288
+ "<BYTE_231>": 231,
289
+ "<BYTE_232>": 232,
290
+ "<BYTE_233>": 233,
291
+ "<BYTE_234>": 234,
292
+ "<BYTE_235>": 235,
293
+ "<BYTE_236>": 236,
294
+ "<BYTE_237>": 237,
295
+ "<BYTE_238>": 238,
296
+ "<BYTE_239>": 239,
297
+ "<BYTE_240>": 240,
298
+ "<BYTE_241>": 241,
299
+ "<BYTE_242>": 242,
300
+ "<BYTE_243>": 243,
301
+ "<BYTE_244>": 244,
302
+ "<BYTE_245>": 245,
303
+ "<BYTE_246>": 246,
304
+ "<BYTE_247>": 247,
305
+ "<BYTE_248>": 248,
306
+ "<BYTE_249>": 249,
307
+ "<BYTE_250>": 250,
308
+ "<BYTE_251>": 251,
309
+ "<BYTE_252>": 252,
310
+ "<BYTE_253>": 253,
311
+ "<BYTE_254>": 254,
312
+ "<BYTE_255>": 255,
313
+ "<DIGIT_0>": 256,
314
+ "<DIGIT_1>": 257,
315
+ "<DIGIT_2>": 258,
316
+ "<DIGIT_3>": 259,
317
+ "<DIGIT_4>": 260,
318
+ "<DIGIT_5>": 261,
319
+ "<DIGIT_6>": 262,
320
+ "<DIGIT_7>": 263,
321
+ "<DIGIT_8>": 264,
322
+ "<DIGIT_9>": 265,
323
+ "<ADD>": 266,
324
+ "<SUB>": 267,
325
+ "<MULTIPLY>": 268,
326
+ "<START>": 269,
327
+ "<STEP>": 270,
328
+ "<FINAL>": 271,
329
+ "<PIPE>": 272,
330
+ "<COLON>": 273,
331
+ "<BOUNDARY>": 274,
332
+ "<PAD>": 275
333
+ },
334
+ "unk_token": "<unk>"
335
+ }
336
+ }
150m-P150s-b15312-m0.5/step_1600/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
+ }