Hugging Face's logo

TomasFAV
/
DonutInvoiceCzechV0

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
 Metrics Community
TomasFAV commited on
Commit
7ac12db
·
verified ·
1 Parent(s): 0abc0fd

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +144 -0
  2. generation_config.json +39 -0
  3. model.safetensors +3 -0
  4. runs/Mar22_10-21-49_5e59ae3c1ae1/events.out.tfevents.1774174909.5e59ae3c1ae1.11931.0 +3 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": true,
10
+ "add_final_layer_norm": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": 0.0,
16
+ "cross_attention_hidden_size": null,
17
+ "d_model": 1024,
18
+ "decoder_attention_heads": 16,
19
+ "decoder_ffn_dim": 4096,
20
+ "decoder_layerdrop": 0.0,
21
+ "decoder_layers": 4,
22
+ "decoder_start_token_id": null,
23
+ "dropout": 0.1,
24
+ "dtype": "float32",
25
+ "encoder_attention_heads": 16,
26
+ "encoder_ffn_dim": 4096,
27
+ "encoder_layerdrop": 0.0,
28
+ "encoder_layers": 12,
29
+ "eos_token_id": 2,
30
+ "finetuning_task": null,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "max_length": 768,
43
+ "max_position_embeddings": 768,
44
+ "model_type": "mbart",
45
+ "num_hidden_layers": 12,
46
+ "output_attentions": false,
47
+ "output_hidden_states": false,
48
+ "pad_token_id": 1,
49
+ "prefix": null,
50
+ "problem_type": null,
51
+ "pruned_heads": {},
52
+ "return_dict": true,
53
+ "scale_embedding": true,
54
+ "sep_token_id": null,
55
+ "task_specific_params": null,
56
+ "tf_legacy_loss": false,
57
+ "tie_encoder_decoder": false,
58
+ "tie_word_embeddings": true,
59
+ "tokenizer_class": null,
60
+ "torchscript": false,
61
+ "use_bfloat16": false,
62
+ "use_cache": true,
63
+ "vocab_size": 57664
64
+ },
65
+ "decoder_start_token_id": 0,
66
+ "dtype": "float32",
67
+ "encoder": {
68
+ "_name_or_path": "",
69
+ "add_cross_attention": false,
70
+ "architectures": null,
71
+ "attention_probs_dropout_prob": 0.0,
72
+ "bos_token_id": null,
73
+ "chunk_size_feed_forward": 0,
74
+ "cross_attention_hidden_size": null,
75
+ "decoder_start_token_id": null,
76
+ "depths": [
77
+ 2,
78
+ 2,
79
+ 14,
80
+ 2
81
+ ],
82
+ "drop_path_rate": 0.1,
83
+ "dtype": "float32",
84
+ "embed_dim": 128,
85
+ "eos_token_id": null,
86
+ "finetuning_task": null,
87
+ "hidden_act": "gelu",
88
+ "hidden_dropout_prob": 0.0,
89
+ "hidden_size": 1024,
90
+ "id2label": {
91
+ "0": "LABEL_0",
92
+ "1": "LABEL_1"
93
+ },
94
+ "image_size": [
95
+ 2338,
96
+ 1654
97
+ ],
98
+ "initializer_range": 0.02,
99
+ "is_decoder": false,
100
+ "is_encoder_decoder": false,
101
+ "label2id": {
102
+ "LABEL_0": 0,
103
+ "LABEL_1": 1
104
+ },
105
+ "layer_norm_eps": 1e-05,
106
+ "mlp_ratio": 4.0,
107
+ "model_type": "donut-swin",
108
+ "num_channels": 3,
109
+ "num_heads": [
110
+ 4,
111
+ 8,
112
+ 16,
113
+ 32
114
+ ],
115
+ "num_layers": 4,
116
+ "output_attentions": false,
117
+ "output_hidden_states": false,
118
+ "pad_token_id": null,
119
+ "patch_size": 4,
120
+ "path_norm": true,
121
+ "prefix": null,
122
+ "problem_type": null,
123
+ "pruned_heads": {},
124
+ "qkv_bias": true,
125
+ "return_dict": true,
126
+ "sep_token_id": null,
127
+ "task_specific_params": null,
128
+ "tf_legacy_loss": false,
129
+ "tie_encoder_decoder": false,
130
+ "tie_word_embeddings": true,
131
+ "tokenizer_class": null,
132
+ "torchscript": false,
133
+ "use_absolute_embeddings": false,
134
+ "use_bfloat16": false,
135
+ "window_size": 10
136
+ },
137
+ "eos_token_id": 2,
138
+ "is_encoder_decoder": true,
139
+ "model_type": "vision-encoder-decoder",
140
+ "pad_token_id": 1,
141
+ "tie_word_embeddings": false,
142
+ "transformers_version": "5.0.0",
143
+ "use_cache": false
144
+ }
generation_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 0,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": false,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 20,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 1,
24
+ "num_return_sequences": 1,
25
+ "output_attentions": false,
26
+ "output_hidden_states": false,
27
+ "output_scores": false,
28
+ "pad_token_id": 1,
29
+ "remove_invalid_values": false,
30
+ "repetition_penalty": 1.0,
31
+ "return_dict_in_generate": false,
32
+ "target_lookbehind": 10,
33
+ "temperature": 1.0,
34
+ "top_k": 50,
35
+ "top_p": 1.0,
36
+ "transformers_version": "5.0.0",
37
+ "typical_p": 1.0,
38
+ "use_cache": true
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6399b6c5968c90192a07e335b18bda556109f3d45a36e926acf06bcb84db94d7
3
+ size 806494360
runs/Mar22_10-21-49_5e59ae3c1ae1/events.out.tfevents.1774174909.5e59ae3c1ae1.11931.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b08eeae90a6e7f4bf14f6009eb6e4e4d62d064b2c65c79e914e8d0e6eaf560d
3
+ size 13941
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98f3cb2b4a37c89958840949039f8a56a1c9e6fbc512d6141a43af943cca1bc
3
+ size 5329