Hugging Face's logo

magistermilitum
/
tridis_v2_HTR_historical_manuscripts

Safetensors
vision-encoder-decoder
handwritten-text-recognition
Image-to-text
Model card Files Community
magistermilitum commited on
Commit
2862541
•
1 Parent(s): db1b6d9

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +177 -0
  2. generation_config.json +13 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. preprocessor_config.json +22 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/trocr-large-handwritten",
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
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": 0.0,
18
+ "cross_attention_hidden_size": 1024,
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": 514,
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
+ "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": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": false,
83
+ "use_learned_position_embeddings": true,
84
+ "vocab_size": 8000
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
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "encoder_stride": 16,
104
+ "eos_token_id": null,
105
+ "exponential_decay_length_penalty": null,
106
+ "finetuning_task": null,
107
+ "forced_bos_token_id": null,
108
+ "forced_eos_token_id": null,
109
+ "hidden_act": "gelu",
110
+ "hidden_dropout_prob": 0.0,
111
+ "hidden_size": 1024,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 384,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 4096,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_norm_eps": 1e-12,
126
+ "length_penalty": 1.0,
127
+ "max_length": 20,
128
+ "min_length": 0,
129
+ "model_type": "vit",
130
+ "no_repeat_ngram_size": 0,
131
+ "num_attention_heads": 16,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_channels": 3,
135
+ "num_hidden_layers": 24,
136
+ "num_return_sequences": 1,
137
+ "output_attentions": false,
138
+ "output_hidden_states": false,
139
+ "output_scores": false,
140
+ "pad_token_id": null,
141
+ "patch_size": 16,
142
+ "prefix": null,
143
+ "problem_type": null,
144
+ "pruned_heads": {},
145
+ "qkv_bias": false,
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tf_legacy_loss": false,
155
+ "tie_encoder_decoder": false,
156
+ "tie_word_embeddings": true,
157
+ "tokenizer_class": null,
158
+ "top_k": 50,
159
+ "top_p": 1.0,
160
+ "torch_dtype": null,
161
+ "torchscript": false,
162
+ "typical_p": 1.0,
163
+ "use_bfloat16": false
164
+ },
165
+ "eos_token_id": 2,
166
+ "is_encoder_decoder": true,
167
+ "length_penalty": 2.0,
168
+ "max_length": 160,
169
+ "model_type": "vision-encoder-decoder",
170
+ "no_repeat_ngram_size": 3,
171
+ "num_beams": 2,
172
+ "pad_token_id": 1,
173
+ "tie_word_embeddings": false,
174
+ "torch_dtype": "float32",
175
+ "transformers_version": "4.35.0",
176
+ "vocab_size": 8000
177
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 0,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "length_penalty": 2.0,
7
+ "max_length": 160,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 2,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.35.0",
12
+ "use_cache": false
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79c620b015af2cee4f83ae492a9f956d94fe687c2b1b5032916e73f13293b04
3
+ size 2298553664
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a673bc5822d73978a963ecab12d133513dfe3e09dc9d6a69c643e12f43579ec9
3
+ size 4523551378
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 384,
20
+ "width": 384
21
+ }
22
+ }
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3e59734179d64415f3fb134312cab843680a1084a8fc8ac4032285325b1c47
3
+ size 1064
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 sha256:06a545d22a974468fd2126d816a713ac50f220f119d18e087e1624502f515969
3
+ size 4792