gagan3012 commited on
Commit
f20195e
·
1 Parent(s): c5478a0

Upload model

Browse files
Files changed (3) hide show
  1. config.json +361 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,361 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "PY007/TinyLlama-1.1B-Chat-v0.1",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "LlamaForCausalLM"
10
+ ],
11
+ "attention_bias": false,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 1,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "silu",
28
+ "hidden_size": 2048,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 5632,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "max_position_embeddings": 2048,
44
+ "min_length": 0,
45
+ "model_type": "llama",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_attention_heads": 32,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_hidden_layers": 22,
51
+ "num_key_value_heads": 4,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": null,
57
+ "prefix": null,
58
+ "pretraining_tp": 1,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": null,
67
+ "rope_theta": 10000.0,
68
+ "sep_token_id": null,
69
+ "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": false,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": "float32",
79
+ "torchscript": false,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": false,
83
+ "vocab_size": 32001
84
+ },
85
+ "encoder": {
86
+ "_name_or_path": "facebook/nougat-base",
87
+ "add_cross_attention": false,
88
+ "architectures": [
89
+ "VisionEncoderDecoderModel"
90
+ ],
91
+ "attention_probs_dropout_prob": 0.0,
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder": {
98
+ "_name_or_path": "",
99
+ "activation_dropout": 0.0,
100
+ "activation_function": "gelu",
101
+ "add_cross_attention": true,
102
+ "add_final_layer_norm": true,
103
+ "architectures": null,
104
+ "attention_dropout": 0.0,
105
+ "bad_words_ids": null,
106
+ "begin_suppress_tokens": null,
107
+ "bos_token_id": 0,
108
+ "chunk_size_feed_forward": 0,
109
+ "classifier_dropout": 0.0,
110
+ "cross_attention_hidden_size": null,
111
+ "d_model": 1024,
112
+ "decoder_attention_heads": 16,
113
+ "decoder_ffn_dim": 4096,
114
+ "decoder_layerdrop": 0.0,
115
+ "decoder_layers": 10,
116
+ "decoder_start_token_id": null,
117
+ "diversity_penalty": 0.0,
118
+ "do_sample": false,
119
+ "dropout": 0.1,
120
+ "early_stopping": false,
121
+ "encoder_attention_heads": 16,
122
+ "encoder_ffn_dim": 4096,
123
+ "encoder_layerdrop": 0.0,
124
+ "encoder_layers": 12,
125
+ "encoder_no_repeat_ngram_size": 0,
126
+ "eos_token_id": 2,
127
+ "exponential_decay_length_penalty": null,
128
+ "finetuning_task": null,
129
+ "forced_bos_token_id": null,
130
+ "forced_eos_token_id": 2,
131
+ "id2label": {
132
+ "0": "LABEL_0",
133
+ "1": "LABEL_1"
134
+ },
135
+ "init_std": 0.02,
136
+ "is_decoder": true,
137
+ "is_encoder_decoder": false,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "max_position_embeddings": 4096,
145
+ "min_length": 0,
146
+ "model_type": "mbart",
147
+ "no_repeat_ngram_size": 0,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_hidden_layers": 12,
151
+ "num_return_sequences": 1,
152
+ "output_attentions": false,
153
+ "output_hidden_states": false,
154
+ "output_scores": false,
155
+ "pad_token_id": 1,
156
+ "prefix": null,
157
+ "problem_type": null,
158
+ "pruned_heads": {},
159
+ "remove_invalid_values": false,
160
+ "repetition_penalty": 1.0,
161
+ "return_dict": true,
162
+ "return_dict_in_generate": false,
163
+ "scale_embedding": true,
164
+ "sep_token_id": null,
165
+ "suppress_tokens": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": false,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "typical_p": 1.0,
177
+ "use_bfloat16": false,
178
+ "use_cache": true,
179
+ "vocab_size": 50000
180
+ },
181
+ "decoder_start_token_id": null,
182
+ "depths": [
183
+ 2,
184
+ 2,
185
+ 6,
186
+ 2
187
+ ],
188
+ "diversity_penalty": 0.0,
189
+ "do_sample": false,
190
+ "drop_path_rate": 0.1,
191
+ "early_stopping": false,
192
+ "embed_dim": 96,
193
+ "encoder": {
194
+ "_name_or_path": "",
195
+ "add_cross_attention": false,
196
+ "architectures": null,
197
+ "attention_probs_dropout_prob": 0.0,
198
+ "bad_words_ids": null,
199
+ "begin_suppress_tokens": null,
200
+ "bos_token_id": null,
201
+ "chunk_size_feed_forward": 0,
202
+ "cross_attention_hidden_size": null,
203
+ "decoder_start_token_id": null,
204
+ "depths": [
205
+ 2,
206
+ 2,
207
+ 14,
208
+ 2
209
+ ],
210
+ "diversity_penalty": 0.0,
211
+ "do_sample": false,
212
+ "drop_path_rate": 0.1,
213
+ "early_stopping": false,
214
+ "embed_dim": 128,
215
+ "encoder_no_repeat_ngram_size": 0,
216
+ "eos_token_id": null,
217
+ "exponential_decay_length_penalty": null,
218
+ "finetuning_task": null,
219
+ "forced_bos_token_id": null,
220
+ "forced_eos_token_id": null,
221
+ "hidden_act": "gelu",
222
+ "hidden_dropout_prob": 0.0,
223
+ "hidden_size": 1024,
224
+ "id2label": {
225
+ "0": "LABEL_0",
226
+ "1": "LABEL_1"
227
+ },
228
+ "image_size": [
229
+ 896,
230
+ 672
231
+ ],
232
+ "initializer_range": 0.02,
233
+ "is_decoder": false,
234
+ "is_encoder_decoder": false,
235
+ "label2id": {
236
+ "LABEL_0": 0,
237
+ "LABEL_1": 1
238
+ },
239
+ "layer_norm_eps": 1e-05,
240
+ "length_penalty": 1.0,
241
+ "max_length": 20,
242
+ "min_length": 0,
243
+ "mlp_ratio": 4.0,
244
+ "model_type": "donut-swin",
245
+ "no_repeat_ngram_size": 0,
246
+ "num_beam_groups": 1,
247
+ "num_beams": 1,
248
+ "num_channels": 3,
249
+ "num_heads": [
250
+ 4,
251
+ 8,
252
+ 16,
253
+ 32
254
+ ],
255
+ "num_layers": 4,
256
+ "num_return_sequences": 1,
257
+ "output_attentions": false,
258
+ "output_hidden_states": false,
259
+ "output_scores": false,
260
+ "pad_token_id": null,
261
+ "patch_size": 4,
262
+ "prefix": null,
263
+ "problem_type": null,
264
+ "pruned_heads": {},
265
+ "qkv_bias": true,
266
+ "remove_invalid_values": false,
267
+ "repetition_penalty": 1.0,
268
+ "return_dict": true,
269
+ "return_dict_in_generate": false,
270
+ "sep_token_id": null,
271
+ "suppress_tokens": null,
272
+ "task_specific_params": null,
273
+ "temperature": 1.0,
274
+ "tf_legacy_loss": false,
275
+ "tie_encoder_decoder": false,
276
+ "tie_word_embeddings": true,
277
+ "tokenizer_class": null,
278
+ "top_k": 50,
279
+ "top_p": 1.0,
280
+ "torch_dtype": null,
281
+ "torchscript": false,
282
+ "typical_p": 1.0,
283
+ "use_absolute_embeddings": false,
284
+ "use_bfloat16": false,
285
+ "window_size": 7
286
+ },
287
+ "encoder_no_repeat_ngram_size": 0,
288
+ "eos_token_id": null,
289
+ "exponential_decay_length_penalty": null,
290
+ "finetuning_task": null,
291
+ "forced_bos_token_id": null,
292
+ "forced_eos_token_id": null,
293
+ "hidden_act": "gelu",
294
+ "hidden_dropout_prob": 0.0,
295
+ "hidden_size": 768,
296
+ "id2label": {
297
+ "0": "LABEL_0",
298
+ "1": "LABEL_1"
299
+ },
300
+ "image_size": 224,
301
+ "initializer_range": 0.02,
302
+ "is_decoder": false,
303
+ "is_encoder_decoder": true,
304
+ "label2id": {
305
+ "LABEL_0": 0,
306
+ "LABEL_1": 1
307
+ },
308
+ "layer_norm_eps": 1e-05,
309
+ "length_penalty": 1.0,
310
+ "max_length": 20,
311
+ "min_length": 0,
312
+ "mlp_ratio": 4.0,
313
+ "model_type": "donut-swin",
314
+ "no_repeat_ngram_size": 0,
315
+ "num_beam_groups": 1,
316
+ "num_beams": 1,
317
+ "num_channels": 3,
318
+ "num_heads": [
319
+ 3,
320
+ 6,
321
+ 12,
322
+ 24
323
+ ],
324
+ "num_layers": 4,
325
+ "num_return_sequences": 1,
326
+ "output_attentions": false,
327
+ "output_hidden_states": false,
328
+ "output_scores": false,
329
+ "pad_token_id": null,
330
+ "patch_size": 4,
331
+ "prefix": null,
332
+ "problem_type": null,
333
+ "pruned_heads": {},
334
+ "qkv_bias": true,
335
+ "remove_invalid_values": false,
336
+ "repetition_penalty": 1.0,
337
+ "return_dict": true,
338
+ "return_dict_in_generate": false,
339
+ "sep_token_id": null,
340
+ "suppress_tokens": null,
341
+ "task_specific_params": null,
342
+ "temperature": 1.0,
343
+ "tf_legacy_loss": false,
344
+ "tie_encoder_decoder": false,
345
+ "tie_word_embeddings": false,
346
+ "tokenizer_class": null,
347
+ "top_k": 50,
348
+ "top_p": 1.0,
349
+ "torch_dtype": "float32",
350
+ "torchscript": false,
351
+ "typical_p": 1.0,
352
+ "use_absolute_embeddings": false,
353
+ "use_bfloat16": false,
354
+ "window_size": 7
355
+ },
356
+ "is_encoder_decoder": true,
357
+ "model_type": "vision-encoder-decoder",
358
+ "tie_word_embeddings": false,
359
+ "torch_dtype": "float32",
360
+ "transformers_version": "4.34.0"
361
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0",
6
+ "use_cache": false
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3bfbb706b3dd12e3dc3ac9b5ece523a24a0275b72bf7c56b9d668cfd153e86
3
+ size 4516956641