Spacyzipa commited on
Commit
8672169
1 Parent(s): 7f04a9d

Training in progress, epoch 0

Browse files
Files changed (2) hide show
  1. config.json +18 -186
  2. pytorch_model.bin +3 -0
config.json CHANGED
@@ -1,192 +1,24 @@
1
  {
2
  "_name_or_path": "naver-clova-ix/donut-base",
 
3
  "architectures": [
4
- "VisionEncoderDecoderModel"
5
  ],
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_dropout": 0.0,
9
- "activation_function": "gelu",
10
- "add_cross_attention": true,
11
- "add_final_layer_norm": true,
12
- "architectures": null,
13
- "attention_dropout": 0.0,
14
- "bad_words_ids": null,
15
- "begin_suppress_tokens": null,
16
- "bos_token_id": 0,
17
- "chunk_size_feed_forward": 0,
18
- "classifier_dropout": 0.0,
19
- "cross_attention_hidden_size": null,
20
- "d_model": 1024,
21
- "decoder_attention_heads": 16,
22
- "decoder_ffn_dim": 4096,
23
- "decoder_layerdrop": 0.0,
24
- "decoder_layers": 4,
25
- "decoder_start_token_id": null,
26
- "diversity_penalty": 0.0,
27
- "do_sample": false,
28
- "dropout": 0.1,
29
- "early_stopping": false,
30
- "encoder_attention_heads": 16,
31
- "encoder_ffn_dim": 4096,
32
- "encoder_layerdrop": 0.0,
33
- "encoder_layers": 12,
34
- "encoder_no_repeat_ngram_size": 0,
35
- "eos_token_id": 2,
36
- "exponential_decay_length_penalty": null,
37
- "finetuning_task": null,
38
- "forced_bos_token_id": null,
39
- "forced_eos_token_id": 2,
40
- "id2label": {
41
- "0": "LABEL_0",
42
- "1": "LABEL_1"
43
- },
44
- "init_std": 0.02,
45
- "is_decoder": true,
46
- "is_encoder_decoder": false,
47
- "label2id": {
48
- "LABEL_0": 0,
49
- "LABEL_1": 1
50
- },
51
- "length_penalty": 1.0,
52
- "max_length": 768,
53
- "max_position_embeddings": 1536,
54
- "min_length": 0,
55
- "model_type": "mbart",
56
- "no_repeat_ngram_size": 0,
57
- "num_beam_groups": 1,
58
- "num_beams": 1,
59
- "num_hidden_layers": 12,
60
- "num_return_sequences": 1,
61
- "output_attentions": false,
62
- "output_hidden_states": false,
63
- "output_scores": false,
64
- "pad_token_id": 1,
65
- "prefix": null,
66
- "problem_type": null,
67
- "pruned_heads": {},
68
- "remove_invalid_values": false,
69
- "repetition_penalty": 1.0,
70
- "return_dict": true,
71
- "return_dict_in_generate": false,
72
- "scale_embedding": true,
73
- "sep_token_id": null,
74
- "suppress_tokens": null,
75
- "task_specific_params": null,
76
- "temperature": 1.0,
77
- "tf_legacy_loss": false,
78
- "tie_encoder_decoder": false,
79
- "tie_word_embeddings": true,
80
- "tokenizer_class": null,
81
- "top_k": 50,
82
- "top_p": 1.0,
83
- "torch_dtype": null,
84
- "torchscript": false,
85
- "typical_p": 1.0,
86
- "use_bfloat16": false,
87
- "use_cache": true,
88
- "vocab_size": 57618
89
- },
90
- "decoder_start_token_id": 57617,
91
- "encoder": {
92
- "_name_or_path": "",
93
- "add_cross_attention": false,
94
- "architectures": null,
95
- "attention_probs_dropout_prob": 0.0,
96
- "bad_words_ids": null,
97
- "begin_suppress_tokens": null,
98
- "bos_token_id": null,
99
- "chunk_size_feed_forward": 0,
100
- "cross_attention_hidden_size": null,
101
- "decoder_start_token_id": null,
102
- "depths": [
103
- 2,
104
- 2,
105
- 14,
106
- 2
107
- ],
108
- "diversity_penalty": 0.0,
109
- "do_sample": false,
110
- "drop_path_rate": 0.1,
111
- "early_stopping": false,
112
- "embed_dim": 128,
113
- "encoder_no_repeat_ngram_size": 0,
114
- "eos_token_id": null,
115
- "exponential_decay_length_penalty": null,
116
- "finetuning_task": null,
117
- "forced_bos_token_id": null,
118
- "forced_eos_token_id": null,
119
- "hidden_act": "gelu",
120
- "hidden_dropout_prob": 0.0,
121
- "hidden_size": 1024,
122
- "id2label": {
123
- "0": "LABEL_0",
124
- "1": "LABEL_1"
125
- },
126
- "image_size": [
127
- 1280,
128
- 960
129
- ],
130
- "initializer_range": 0.02,
131
- "is_decoder": false,
132
- "is_encoder_decoder": false,
133
- "label2id": {
134
- "LABEL_0": 0,
135
- "LABEL_1": 1
136
- },
137
- "layer_norm_eps": 1e-05,
138
- "length_penalty": 1.0,
139
- "max_length": 20,
140
- "min_length": 0,
141
- "mlp_ratio": 4.0,
142
- "model_type": "donut-swin",
143
- "no_repeat_ngram_size": 0,
144
- "num_beam_groups": 1,
145
- "num_beams": 1,
146
- "num_channels": 3,
147
- "num_heads": [
148
- 4,
149
- 8,
150
- 16,
151
- 32
152
- ],
153
- "num_layers": 4,
154
- "num_return_sequences": 1,
155
- "output_attentions": false,
156
- "output_hidden_states": false,
157
- "output_scores": false,
158
- "pad_token_id": null,
159
- "patch_size": 4,
160
- "path_norm": true,
161
- "prefix": null,
162
- "problem_type": null,
163
- "pruned_heads": {},
164
- "qkv_bias": true,
165
- "remove_invalid_values": false,
166
- "repetition_penalty": 1.0,
167
- "return_dict": true,
168
- "return_dict_in_generate": false,
169
- "sep_token_id": null,
170
- "suppress_tokens": null,
171
- "task_specific_params": null,
172
- "temperature": 1.0,
173
- "tf_legacy_loss": false,
174
- "tie_encoder_decoder": false,
175
- "tie_word_embeddings": true,
176
- "tokenizer_class": null,
177
- "top_k": 50,
178
- "top_p": 1.0,
179
- "torch_dtype": null,
180
- "torchscript": false,
181
- "typical_p": 1.0,
182
- "use_absolute_embeddings": false,
183
- "use_bfloat16": false,
184
- "window_size": 10
185
- },
186
- "is_encoder_decoder": true,
187
- "model_type": "vision-encoder-decoder",
188
- "pad_token_id": 1,
189
- "tie_word_embeddings": false,
190
  "torch_dtype": "float32",
191
- "transformers_version": "4.35.2"
 
192
  }
 
1
  {
2
  "_name_or_path": "naver-clova-ix/donut-base",
3
+ "align_long_axis": false,
4
  "architectures": [
5
+ "DonutModel"
6
  ],
7
+ "decoder_layer": 4,
8
+ "encoder_layer": [
9
+ 2,
10
+ 2,
11
+ 14,
12
+ 2
13
+ ],
14
+ "input_size": [
15
+ 1280,
16
+ 960
17
+ ],
18
+ "max_length": 768,
19
+ "max_position_embeddings": 768,
20
+ "model_type": "donut",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
+ "window_size": 10
24
  }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bf5267d6a44e6e6edfccf8078f0ed3778af2740487355b97e77eedbccdd2ba
3
+ size 858346238