Kalslice commited on
Commit
c56ccc8
1 Parent(s): 4965a46

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +305 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-large",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
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": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
19
+ "n_positions": 1024,
20
+ "output_attentions": true,
21
+ "pruned_heads": {
22
+ "8": [
23
+ 1,
24
+ 14
25
+ ],
26
+ "10": [
27
+ 1,
28
+ 15
29
+ ],
30
+ "11": [
31
+ 19,
32
+ 12,
33
+ 13
34
+ ],
35
+ "12": [
36
+ 18,
37
+ 3,
38
+ 13
39
+ ],
40
+ "13": [
41
+ 4,
42
+ 15,
43
+ 6,
44
+ 7
45
+ ],
46
+ "15": [
47
+ 1,
48
+ 4,
49
+ 17
50
+ ],
51
+ "16": [
52
+ 0,
53
+ 2,
54
+ 6,
55
+ 9,
56
+ 15
57
+ ],
58
+ "17": [
59
+ 16,
60
+ 17,
61
+ 4,
62
+ 6,
63
+ 11,
64
+ 13
65
+ ],
66
+ "18": [
67
+ 9,
68
+ 19,
69
+ 4,
70
+ 7
71
+ ],
72
+ "19": [
73
+ 17,
74
+ 2,
75
+ 18,
76
+ 4,
77
+ 8,
78
+ 11
79
+ ],
80
+ "20": [
81
+ 0,
82
+ 1,
83
+ 4,
84
+ 7,
85
+ 10,
86
+ 11,
87
+ 15,
88
+ 16,
89
+ 17,
90
+ 18,
91
+ 19
92
+ ],
93
+ "21": [
94
+ 17,
95
+ 19,
96
+ 4,
97
+ 5,
98
+ 8,
99
+ 12,
100
+ 14,
101
+ 15
102
+ ],
103
+ "22": [
104
+ 0,
105
+ 18,
106
+ 3,
107
+ 4,
108
+ 19,
109
+ 13,
110
+ 14
111
+ ],
112
+ "23": [
113
+ 0,
114
+ 3,
115
+ 5,
116
+ 7,
117
+ 8,
118
+ 12,
119
+ 13,
120
+ 15
121
+ ],
122
+ "24": [
123
+ 1,
124
+ 5,
125
+ 6,
126
+ 8,
127
+ 11,
128
+ 13,
129
+ 14,
130
+ 15,
131
+ 16,
132
+ 18,
133
+ 19
134
+ ],
135
+ "25": [
136
+ 0,
137
+ 3,
138
+ 5,
139
+ 6,
140
+ 7,
141
+ 10,
142
+ 13,
143
+ 14,
144
+ 15,
145
+ 16,
146
+ 18,
147
+ 19
148
+ ],
149
+ "26": [
150
+ 0,
151
+ 1,
152
+ 3,
153
+ 6,
154
+ 8,
155
+ 10,
156
+ 13,
157
+ 14,
158
+ 15,
159
+ 16,
160
+ 17
161
+ ],
162
+ "27": [
163
+ 0,
164
+ 1,
165
+ 2,
166
+ 6,
167
+ 7,
168
+ 13,
169
+ 14,
170
+ 16,
171
+ 17
172
+ ],
173
+ "28": [
174
+ 0,
175
+ 1,
176
+ 2,
177
+ 3,
178
+ 4,
179
+ 6,
180
+ 7,
181
+ 8,
182
+ 9,
183
+ 10,
184
+ 12,
185
+ 14,
186
+ 16,
187
+ 17,
188
+ 19
189
+ ],
190
+ "29": [
191
+ 0,
192
+ 1,
193
+ 2,
194
+ 3,
195
+ 5,
196
+ 7,
197
+ 8,
198
+ 9,
199
+ 10,
200
+ 11,
201
+ 12,
202
+ 13,
203
+ 14,
204
+ 15,
205
+ 16,
206
+ 17,
207
+ 18,
208
+ 19
209
+ ],
210
+ "30": [
211
+ 0,
212
+ 1,
213
+ 2,
214
+ 3,
215
+ 4,
216
+ 7,
217
+ 8,
218
+ 9,
219
+ 10,
220
+ 11,
221
+ 12,
222
+ 14,
223
+ 15,
224
+ 16,
225
+ 17,
226
+ 18,
227
+ 19
228
+ ],
229
+ "31": [
230
+ 0,
231
+ 1,
232
+ 2,
233
+ 4,
234
+ 5,
235
+ 6,
236
+ 7,
237
+ 8,
238
+ 9,
239
+ 10,
240
+ 11,
241
+ 12,
242
+ 14,
243
+ 15,
244
+ 16,
245
+ 17,
246
+ 18,
247
+ 19
248
+ ],
249
+ "32": [
250
+ 0,
251
+ 6,
252
+ 7,
253
+ 8,
254
+ 9,
255
+ 10,
256
+ 12,
257
+ 13,
258
+ 14,
259
+ 15,
260
+ 16,
261
+ 17,
262
+ 19
263
+ ],
264
+ "33": [
265
+ 0,
266
+ 1,
267
+ 2,
268
+ 3,
269
+ 4,
270
+ 6,
271
+ 9,
272
+ 10,
273
+ 12,
274
+ 13,
275
+ 14,
276
+ 15,
277
+ 17,
278
+ 18,
279
+ 19
280
+ ],
281
+ "34": [
282
+ 18,
283
+ 7
284
+ ]
285
+ },
286
+ "reorder_and_upcast_attn": false,
287
+ "resid_pdrop": 0.1,
288
+ "scale_attn_by_inverse_layer_idx": false,
289
+ "scale_attn_weights": true,
290
+ "summary_activation": null,
291
+ "summary_first_dropout": 0.1,
292
+ "summary_proj_to_labels": true,
293
+ "summary_type": "cls_index",
294
+ "summary_use_proj": true,
295
+ "task_specific_params": {
296
+ "text-generation": {
297
+ "do_sample": true,
298
+ "max_length": 50
299
+ }
300
+ },
301
+ "torch_dtype": "float32",
302
+ "transformers_version": "4.36.2",
303
+ "use_cache": true,
304
+ "vocab_size": 50257
305
+ }
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": "4.36.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6721470b4289f260556de522252e948ec0264e7400333eb2a7b67ca008ff6ab3
3
+ size 2816818936
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ac0c9a67b4e46868d52cad8409cc909640809d3ba948794c30839d13e4e271
3
+ size 4283