Hugging Face's logo

DistillationDiffusion
/
ModelFineTunedCheckpointsReal

Safetensors
Model card Files
xet
 Community
DrewPhi commited on
Commit
affd5bc
·
verified ·
1 Parent(s): 07ab7d7

Upload teacher checkpoint pythia2p8b

Browse files
Files changed (9) hide show
  1. teacher_checkpoints/clinc_fine/pythia2p8b/checkpoint_metrics.json +5 -0
  2. teacher_checkpoints/clinc_fine/pythia2p8b/config.json +337 -0
  3. teacher_checkpoints/clinc_fine/pythia2p8b/model-00001-of-00003.safetensors +3 -0
  4. teacher_checkpoints/clinc_fine/pythia2p8b/model-00002-of-00003.safetensors +3 -0
  5. teacher_checkpoints/clinc_fine/pythia2p8b/model-00003-of-00003.safetensors +3 -0
  6. teacher_checkpoints/clinc_fine/pythia2p8b/model.safetensors.index.json +396 -0
  7. teacher_checkpoints/clinc_fine/pythia2p8b/special_tokens_map.json +24 -0
  8. teacher_checkpoints/clinc_fine/pythia2p8b/tokenizer.json +0 -0
  9. teacher_checkpoints/clinc_fine/pythia2p8b/tokenizer_config.json +215 -0
teacher_checkpoints/clinc_fine/pythia2p8b/checkpoint_metrics.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "update": 175,
3
+ "heldout_accuracy": 0.9166666666666666,
4
+ "heldout_loss": 0.4620456837716131
5
+ }
teacher_checkpoints/clinc_fine/pythia2p8b/config.json ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "dtype": "float32",
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2560,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13",
29
+ "14": "LABEL_14",
30
+ "15": "LABEL_15",
31
+ "16": "LABEL_16",
32
+ "17": "LABEL_17",
33
+ "18": "LABEL_18",
34
+ "19": "LABEL_19",
35
+ "20": "LABEL_20",
36
+ "21": "LABEL_21",
37
+ "22": "LABEL_22",
38
+ "23": "LABEL_23",
39
+ "24": "LABEL_24",
40
+ "25": "LABEL_25",
41
+ "26": "LABEL_26",
42
+ "27": "LABEL_27",
43
+ "28": "LABEL_28",
44
+ "29": "LABEL_29",
45
+ "30": "LABEL_30",
46
+ "31": "LABEL_31",
47
+ "32": "LABEL_32",
48
+ "33": "LABEL_33",
49
+ "34": "LABEL_34",
50
+ "35": "LABEL_35",
51
+ "36": "LABEL_36",
52
+ "37": "LABEL_37",
53
+ "38": "LABEL_38",
54
+ "39": "LABEL_39",
55
+ "40": "LABEL_40",
56
+ "41": "LABEL_41",
57
+ "42": "LABEL_42",
58
+ "43": "LABEL_43",
59
+ "44": "LABEL_44",
60
+ "45": "LABEL_45",
61
+ "46": "LABEL_46",
62
+ "47": "LABEL_47",
63
+ "48": "LABEL_48",
64
+ "49": "LABEL_49",
65
+ "50": "LABEL_50",
66
+ "51": "LABEL_51",
67
+ "52": "LABEL_52",
68
+ "53": "LABEL_53",
69
+ "54": "LABEL_54",
70
+ "55": "LABEL_55",
71
+ "56": "LABEL_56",
72
+ "57": "LABEL_57",
73
+ "58": "LABEL_58",
74
+ "59": "LABEL_59",
75
+ "60": "LABEL_60",
76
+ "61": "LABEL_61",
77
+ "62": "LABEL_62",
78
+ "63": "LABEL_63",
79
+ "64": "LABEL_64",
80
+ "65": "LABEL_65",
81
+ "66": "LABEL_66",
82
+ "67": "LABEL_67",
83
+ "68": "LABEL_68",
84
+ "69": "LABEL_69",
85
+ "70": "LABEL_70",
86
+ "71": "LABEL_71",
87
+ "72": "LABEL_72",
88
+ "73": "LABEL_73",
89
+ "74": "LABEL_74",
90
+ "75": "LABEL_75",
91
+ "76": "LABEL_76",
92
+ "77": "LABEL_77",
93
+ "78": "LABEL_78",
94
+ "79": "LABEL_79",
95
+ "80": "LABEL_80",
96
+ "81": "LABEL_81",
97
+ "82": "LABEL_82",
98
+ "83": "LABEL_83",
99
+ "84": "LABEL_84",
100
+ "85": "LABEL_85",
101
+ "86": "LABEL_86",
102
+ "87": "LABEL_87",
103
+ "88": "LABEL_88",
104
+ "89": "LABEL_89",
105
+ "90": "LABEL_90",
106
+ "91": "LABEL_91",
107
+ "92": "LABEL_92",
108
+ "93": "LABEL_93",
109
+ "94": "LABEL_94",
110
+ "95": "LABEL_95",
111
+ "96": "LABEL_96",
112
+ "97": "LABEL_97",
113
+ "98": "LABEL_98",
114
+ "99": "LABEL_99",
115
+ "100": "LABEL_100",
116
+ "101": "LABEL_101",
117
+ "102": "LABEL_102",
118
+ "103": "LABEL_103",
119
+ "104": "LABEL_104",
120
+ "105": "LABEL_105",
121
+ "106": "LABEL_106",
122
+ "107": "LABEL_107",
123
+ "108": "LABEL_108",
124
+ "109": "LABEL_109",
125
+ "110": "LABEL_110",
126
+ "111": "LABEL_111",
127
+ "112": "LABEL_112",
128
+ "113": "LABEL_113",
129
+ "114": "LABEL_114",
130
+ "115": "LABEL_115",
131
+ "116": "LABEL_116",
132
+ "117": "LABEL_117",
133
+ "118": "LABEL_118",
134
+ "119": "LABEL_119",
135
+ "120": "LABEL_120",
136
+ "121": "LABEL_121",
137
+ "122": "LABEL_122",
138
+ "123": "LABEL_123",
139
+ "124": "LABEL_124",
140
+ "125": "LABEL_125",
141
+ "126": "LABEL_126",
142
+ "127": "LABEL_127",
143
+ "128": "LABEL_128",
144
+ "129": "LABEL_129",
145
+ "130": "LABEL_130",
146
+ "131": "LABEL_131",
147
+ "132": "LABEL_132",
148
+ "133": "LABEL_133",
149
+ "134": "LABEL_134",
150
+ "135": "LABEL_135",
151
+ "136": "LABEL_136",
152
+ "137": "LABEL_137",
153
+ "138": "LABEL_138",
154
+ "139": "LABEL_139",
155
+ "140": "LABEL_140",
156
+ "141": "LABEL_141",
157
+ "142": "LABEL_142",
158
+ "143": "LABEL_143",
159
+ "144": "LABEL_144",
160
+ "145": "LABEL_145",
161
+ "146": "LABEL_146",
162
+ "147": "LABEL_147",
163
+ "148": "LABEL_148",
164
+ "149": "LABEL_149"
165
+ },
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 10240,
168
+ "label2id": {
169
+ "LABEL_0": 0,
170
+ "LABEL_1": 1,
171
+ "LABEL_10": 10,
172
+ "LABEL_100": 100,
173
+ "LABEL_101": 101,
174
+ "LABEL_102": 102,
175
+ "LABEL_103": 103,
176
+ "LABEL_104": 104,
177
+ "LABEL_105": 105,
178
+ "LABEL_106": 106,
179
+ "LABEL_107": 107,
180
+ "LABEL_108": 108,
181
+ "LABEL_109": 109,
182
+ "LABEL_11": 11,
183
+ "LABEL_110": 110,
184
+ "LABEL_111": 111,
185
+ "LABEL_112": 112,
186
+ "LABEL_113": 113,
187
+ "LABEL_114": 114,
188
+ "LABEL_115": 115,
189
+ "LABEL_116": 116,
190
+ "LABEL_117": 117,
191
+ "LABEL_118": 118,
192
+ "LABEL_119": 119,
193
+ "LABEL_12": 12,
194
+ "LABEL_120": 120,
195
+ "LABEL_121": 121,
196
+ "LABEL_122": 122,
197
+ "LABEL_123": 123,
198
+ "LABEL_124": 124,
199
+ "LABEL_125": 125,
200
+ "LABEL_126": 126,
201
+ "LABEL_127": 127,
202
+ "LABEL_128": 128,
203
+ "LABEL_129": 129,
204
+ "LABEL_13": 13,
205
+ "LABEL_130": 130,
206
+ "LABEL_131": 131,
207
+ "LABEL_132": 132,
208
+ "LABEL_133": 133,
209
+ "LABEL_134": 134,
210
+ "LABEL_135": 135,
211
+ "LABEL_136": 136,
212
+ "LABEL_137": 137,
213
+ "LABEL_138": 138,
214
+ "LABEL_139": 139,
215
+ "LABEL_14": 14,
216
+ "LABEL_140": 140,
217
+ "LABEL_141": 141,
218
+ "LABEL_142": 142,
219
+ "LABEL_143": 143,
220
+ "LABEL_144": 144,
221
+ "LABEL_145": 145,
222
+ "LABEL_146": 146,
223
+ "LABEL_147": 147,
224
+ "LABEL_148": 148,
225
+ "LABEL_149": 149,
226
+ "LABEL_15": 15,
227
+ "LABEL_16": 16,
228
+ "LABEL_17": 17,
229
+ "LABEL_18": 18,
230
+ "LABEL_19": 19,
231
+ "LABEL_2": 2,
232
+ "LABEL_20": 20,
233
+ "LABEL_21": 21,
234
+ "LABEL_22": 22,
235
+ "LABEL_23": 23,
236
+ "LABEL_24": 24,
237
+ "LABEL_25": 25,
238
+ "LABEL_26": 26,
239
+ "LABEL_27": 27,
240
+ "LABEL_28": 28,
241
+ "LABEL_29": 29,
242
+ "LABEL_3": 3,
243
+ "LABEL_30": 30,
244
+ "LABEL_31": 31,
245
+ "LABEL_32": 32,
246
+ "LABEL_33": 33,
247
+ "LABEL_34": 34,
248
+ "LABEL_35": 35,
249
+ "LABEL_36": 36,
250
+ "LABEL_37": 37,
251
+ "LABEL_38": 38,
252
+ "LABEL_39": 39,
253
+ "LABEL_4": 4,
254
+ "LABEL_40": 40,
255
+ "LABEL_41": 41,
256
+ "LABEL_42": 42,
257
+ "LABEL_43": 43,
258
+ "LABEL_44": 44,
259
+ "LABEL_45": 45,
260
+ "LABEL_46": 46,
261
+ "LABEL_47": 47,
262
+ "LABEL_48": 48,
263
+ "LABEL_49": 49,
264
+ "LABEL_5": 5,
265
+ "LABEL_50": 50,
266
+ "LABEL_51": 51,
267
+ "LABEL_52": 52,
268
+ "LABEL_53": 53,
269
+ "LABEL_54": 54,
270
+ "LABEL_55": 55,
271
+ "LABEL_56": 56,
272
+ "LABEL_57": 57,
273
+ "LABEL_58": 58,
274
+ "LABEL_59": 59,
275
+ "LABEL_6": 6,
276
+ "LABEL_60": 60,
277
+ "LABEL_61": 61,
278
+ "LABEL_62": 62,
279
+ "LABEL_63": 63,
280
+ "LABEL_64": 64,
281
+ "LABEL_65": 65,
282
+ "LABEL_66": 66,
283
+ "LABEL_67": 67,
284
+ "LABEL_68": 68,
285
+ "LABEL_69": 69,
286
+ "LABEL_7": 7,
287
+ "LABEL_70": 70,
288
+ "LABEL_71": 71,
289
+ "LABEL_72": 72,
290
+ "LABEL_73": 73,
291
+ "LABEL_74": 74,
292
+ "LABEL_75": 75,
293
+ "LABEL_76": 76,
294
+ "LABEL_77": 77,
295
+ "LABEL_78": 78,
296
+ "LABEL_79": 79,
297
+ "LABEL_8": 8,
298
+ "LABEL_80": 80,
299
+ "LABEL_81": 81,
300
+ "LABEL_82": 82,
301
+ "LABEL_83": 83,
302
+ "LABEL_84": 84,
303
+ "LABEL_85": 85,
304
+ "LABEL_86": 86,
305
+ "LABEL_87": 87,
306
+ "LABEL_88": 88,
307
+ "LABEL_89": 89,
308
+ "LABEL_9": 9,
309
+ "LABEL_90": 90,
310
+ "LABEL_91": 91,
311
+ "LABEL_92": 92,
312
+ "LABEL_93": 93,
313
+ "LABEL_94": 94,
314
+ "LABEL_95": 95,
315
+ "LABEL_96": 96,
316
+ "LABEL_97": 97,
317
+ "LABEL_98": 98,
318
+ "LABEL_99": 99
319
+ },
320
+ "layer_norm_eps": 1e-05,
321
+ "max_position_embeddings": 2048,
322
+ "model_type": "gpt_neox",
323
+ "num_attention_heads": 32,
324
+ "num_hidden_layers": 32,
325
+ "pad_token_id": 0,
326
+ "partial_rotary_factor": 0.25,
327
+ "problem_type": "single_label_classification",
328
+ "rope_scaling": null,
329
+ "rope_theta": 10000,
330
+ "rotary_emb_base": 10000,
331
+ "rotary_pct": 0.25,
332
+ "tie_word_embeddings": false,
333
+ "transformers_version": "4.57.6",
334
+ "use_cache": false,
335
+ "use_parallel_residual": true,
336
+ "vocab_size": 50304
337
+ }
teacher_checkpoints/clinc_fine/pythia2p8b/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2c9a23c45de5c488afc29d18209ebde47216bb5f53c0c30c6feb58349df693
3
+ size 4999731368
teacher_checkpoints/clinc_fine/pythia2p8b/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9566d14ed5bd9d58cf929c61e28f7ec8c8633281e58eb137a842bf9bb2f7cab9
3
+ size 4956643296
teacher_checkpoints/clinc_fine/pythia2p8b/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad7d86b3713d393d41de01ba20b4c77b9fcc67923bb719ea3b4500fd78d59a4
3
+ size 630930000
teacher_checkpoints/clinc_fine/pythia2p8b/model.safetensors.index.json ADDED
@@ -0,0 +1,396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 2646814720,
4
+ "total_size": 10587258880
5
+ },
6
+ "weight_map": {
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00003.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00003.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00003.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00003.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00003.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
106
+ "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
107
+ "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
108
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
109
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
110
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
111
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
113
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
114
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
115
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
116
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
117
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
118
+ "gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
119
+ "gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
120
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
121
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
122
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
123
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
124
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
125
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
126
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
127
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
128
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
129
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
131
+ "gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
132
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
133
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
134
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
135
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
136
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
137
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
138
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
139
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
140
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
141
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
142
+ "gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
143
+ "gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
144
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
145
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
146
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
147
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
149
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
150
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
151
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
152
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
153
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
154
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
155
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
156
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
157
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
158
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
159
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
160
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
161
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
162
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
163
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
164
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
165
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
166
+ "gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
167
+ "gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
168
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
169
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
170
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
171
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
172
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
173
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
174
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
175
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
176
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
177
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
178
+ "gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
179
+ "gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
180
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
181
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
182
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
183
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
185
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
186
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
187
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
188
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
189
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
191
+ "gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
192
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
193
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
194
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
195
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
196
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
197
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
198
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
199
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
200
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
201
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
203
+ "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
204
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
205
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
206
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
207
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
208
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
209
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
210
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
211
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
212
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
213
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
214
+ "gpt_neox.layers.24.attention.dense.bias": "model-00002-of-00003.safetensors",
215
+ "gpt_neox.layers.24.attention.dense.weight": "model-00002-of-00003.safetensors",
216
+ "gpt_neox.layers.24.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
217
+ "gpt_neox.layers.24.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
218
+ "gpt_neox.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
219
+ "gpt_neox.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
220
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
221
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
222
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
223
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
224
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
225
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
226
+ "gpt_neox.layers.25.attention.dense.bias": "model-00002-of-00003.safetensors",
227
+ "gpt_neox.layers.25.attention.dense.weight": "model-00002-of-00003.safetensors",
228
+ "gpt_neox.layers.25.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
229
+ "gpt_neox.layers.25.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
230
+ "gpt_neox.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
231
+ "gpt_neox.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
232
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
233
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
234
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
235
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
236
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
237
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
238
+ "gpt_neox.layers.26.attention.dense.bias": "model-00002-of-00003.safetensors",
239
+ "gpt_neox.layers.26.attention.dense.weight": "model-00002-of-00003.safetensors",
240
+ "gpt_neox.layers.26.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
241
+ "gpt_neox.layers.26.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
242
+ "gpt_neox.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
243
+ "gpt_neox.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
244
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
245
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
246
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
247
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
248
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
249
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
250
+ "gpt_neox.layers.27.attention.dense.bias": "model-00002-of-00003.safetensors",
251
+ "gpt_neox.layers.27.attention.dense.weight": "model-00002-of-00003.safetensors",
252
+ "gpt_neox.layers.27.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
253
+ "gpt_neox.layers.27.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
254
+ "gpt_neox.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
255
+ "gpt_neox.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
257
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
258
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
259
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
260
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
261
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
262
+ "gpt_neox.layers.28.attention.dense.bias": "model-00002-of-00003.safetensors",
263
+ "gpt_neox.layers.28.attention.dense.weight": "model-00002-of-00003.safetensors",
264
+ "gpt_neox.layers.28.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
265
+ "gpt_neox.layers.28.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
266
+ "gpt_neox.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
267
+ "gpt_neox.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
268
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
269
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
270
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
271
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
272
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
273
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
274
+ "gpt_neox.layers.29.attention.dense.bias": "model-00002-of-00003.safetensors",
275
+ "gpt_neox.layers.29.attention.dense.weight": "model-00002-of-00003.safetensors",
276
+ "gpt_neox.layers.29.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
277
+ "gpt_neox.layers.29.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
278
+ "gpt_neox.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
279
+ "gpt_neox.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
280
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
281
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
282
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
283
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
284
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
285
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
286
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
287
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
288
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
289
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
290
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
291
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
293
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
294
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
295
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
296
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
297
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
298
+ "gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
299
+ "gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
300
+ "gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
301
+ "gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
302
+ "gpt_neox.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors",
303
+ "gpt_neox.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
304
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
305
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
306
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
307
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
308
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
309
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
311
+ "gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
312
+ "gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
313
+ "gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
314
+ "gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
315
+ "gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
316
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
317
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
318
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
319
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
320
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
321
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
322
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
323
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
324
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
325
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
326
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
327
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
329
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
330
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
331
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
332
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
333
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
334
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
335
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
336
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
337
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
338
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
339
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
340
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
341
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
342
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
343
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
344
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
345
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
347
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
348
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
349
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
350
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
351
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
352
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
353
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
354
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
355
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
356
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
357
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
358
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
359
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
360
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
361
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
362
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
363
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
364
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
365
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
366
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
367
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
368
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
369
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
370
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
371
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
372
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
373
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
374
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
375
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
376
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
377
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
378
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
379
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
380
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
381
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
382
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
383
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
384
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
385
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
386
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
387
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
388
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
389
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
390
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
391
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
392
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
393
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
394
+ "score.weight": "model-00003-of-00003.safetensors"
395
+ }
396
+ }
teacher_checkpoints/clinc_fine/pythia2p8b/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
teacher_checkpoints/clinc_fine/pythia2p8b/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
teacher_checkpoints/clinc_fine/pythia2p8b/tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": false,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "model_max_length": 1000000000000000019884624838656,
212
+ "pad_token": "<|endoftext|>",
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
+ "unk_token": "<|endoftext|>"
215
+ }