Hugging Face's logo

dh-unibe
/
trocr-kurrent

Image-Text-to-Text
Transformers
PyTorch
Safetensors
German
vision-encoder-decoder
kurrent
ocr
htr
19th century
Inference Endpoints
Model card Files Community
1
Jonas Widmer commited on
Commit
ac8bcba
•
1 Parent(s): 7c5112b

Init

Browse files
Files changed (9) hide show
  1. config.json +175 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +17 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scaler.pt +3 -0
  7. scheduler.pt +3 -0
  8. trainer_state.json +0 -0
  9. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "69659a277424eb381574e4952f3b3fa3440a419b",
3
+ "_name_or_path": "microsoft/trocr-base-handwritten",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "gelu",
11
+ "add_cross_attention": true,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": 0.0,
18
+ "cross_attention_hidden_size": 768,
19
+ "d_model": 1024,
20
+ "decoder_attention_heads": 16,
21
+ "decoder_ffn_dim": 4096,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 12,
24
+ "decoder_start_token_id": 2,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "dropout": 0.1,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": 2,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_decoder": true,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layernorm_embedding": true,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 512,
50
+ "min_length": 0,
51
+ "model_type": "trocr",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "scale_embedding": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tf_legacy_loss": false,
72
+ "tie_encoder_decoder": false,
73
+ "tie_word_embeddings": true,
74
+ "tokenizer_class": null,
75
+ "top_k": 50,
76
+ "top_p": 1.0,
77
+ "torch_dtype": null,
78
+ "torchscript": false,
79
+ "transformers_version": "4.22.2",
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": false,
83
+ "use_learned_position_embeddings": true,
84
+ "vocab_size": 50265
85
+ },
86
+ "decoder_start_token_id": 0,
87
+ "early_stopping": true,
88
+ "encoder": {
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_probs_dropout_prob": 0.0,
93
+ "bad_words_ids": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "encoder_stride": 16,
103
+ "eos_token_id": null,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_dropout_prob": 0.0,
110
+ "hidden_size": 768,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "image_size": 384,
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 3072,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-12,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "vit",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 12,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_channels": 3,
134
+ "num_hidden_layers": 12,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "patch_size": 16,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "qkv_bias": false,
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tf_legacy_loss": false,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": null,
159
+ "torchscript": false,
160
+ "transformers_version": "4.22.2",
161
+ "typical_p": 1.0,
162
+ "use_bfloat16": false
163
+ },
164
+ "eos_token_id": 2,
165
+ "is_encoder_decoder": true,
166
+ "length_penalty": 2.0,
167
+ "max_length": 128,
168
+ "model_type": "vision-encoder-decoder",
169
+ "num_beams": 4,
170
+ "pad_token_id": 1,
171
+ "tie_word_embeddings": false,
172
+ "torch_dtype": "float32",
173
+ "transformers_version": null,
174
+ "vocab_size": 50265
175
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4e029f806402a095fd728b480e06fab38d019bfccea95c11ddbb83e80470a1
3
+ size 4078814
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 384
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02bdabbb33b897784a6b074f1ee3cc3c1a58ee1ebced72b25126b762929f35a
3
+ size 1335854221
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b05d5450c9c29c6fd1a956373e8f37871380a13621476c72bb50b5143bb782
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca28e537b07b89b3d982116c6f00d83cf311395f81e14ac090680600db56fa99
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519a9af97986ce07be30f1e390d809fa6dc04324d67ee367f177bf4f0f85afa8
3
+ size 627
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a403686da889b7317126062fe6ef411418cd816c8b90b127deac9c4c070c17
3
+ size 3515