Hugging Face's logo

sivan22
/
hdd-words-ocr

Image-to-Text
Transformers
PyTorch
TensorBoard
Safetensors
Hebrew
vision-encoder-decoder
Inference Endpoints
Model card Files Metrics Community
1
sivan22 commited on
Commit
dd781c3
•
1 Parent(s): a672bb0

Training in progress, step 100

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +182 -0
  3. preprocessor_config.json +22 -0
  4. pytorch_model.bin +3 -0
  5. runs/May17_11-28-15_4e0a98886f12/1684322905.9627256/events.out.tfevents.1684322905.4e0a98886f12.31.1 +3 -0
  6. runs/May17_11-28-15_4e0a98886f12/events.out.tfevents.1684322905.4e0a98886f12.31.0 +3 -0
  7. runs/May17_11-31-37_4e0a98886f12/1684323100.3542142/events.out.tfevents.1684323100.4e0a98886f12.31.3 +3 -0
  8. runs/May17_11-31-37_4e0a98886f12/events.out.tfevents.1684323100.4e0a98886f12.31.2 +3 -0
  9. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "imvladikon/alephbertgimmel-base-512",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 512,
49
+ "min_length": 0,
50
+ "model_type": "bert",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "absolute",
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "transformers_version": "4.28.1",
82
+ "type_vocab_size": 2,
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 128000
87
+ },
88
+ "decoder_start_token_id": 1,
89
+ "early_stopping": true,
90
+ "encoder": {
91
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "ViTModel"
95
+ ],
96
+ "attention_probs_dropout_prob": 0.0,
97
+ "bad_words_ids": null,
98
+ "begin_suppress_tokens": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "encoder_stride": 16,
108
+ "eos_token_id": null,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "gelu",
114
+ "hidden_dropout_prob": 0.0,
115
+ "hidden_size": 768,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "image_size": 224,
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_eps": 1e-12,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "min_length": 0,
133
+ "model_type": "vit",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 12,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_channels": 3,
139
+ "num_hidden_layers": 12,
140
+ "num_return_sequences": 1,
141
+ "output_attentions": false,
142
+ "output_hidden_states": false,
143
+ "output_scores": false,
144
+ "pad_token_id": null,
145
+ "patch_size": 16,
146
+ "prefix": null,
147
+ "problem_type": null,
148
+ "pruned_heads": {},
149
+ "qkv_bias": true,
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": true,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": null,
165
+ "torchscript": false,
166
+ "transformers_version": "4.28.1",
167
+ "typical_p": 1.0,
168
+ "use_bfloat16": false
169
+ },
170
+ "eos_token_id": 2,
171
+ "is_encoder_decoder": true,
172
+ "length_penalty": 2.0,
173
+ "max_length": 5,
174
+ "model_type": "vision-encoder-decoder",
175
+ "no_repeat_ngram_size": 3,
176
+ "num_beams": 4,
177
+ "pad_token_id": 3,
178
+ "tie_word_embeddings": false,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null,
181
+ "vocab_size": 128000
182
+ }
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": 224,
20
+ "width": 224
21
+ }
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee2c6f549fa2f9541b26b5c6f063fde015dcef40eba3af9c2a6c0bdd85fd98d
3
+ size 1197111289
runs/May17_11-28-15_4e0a98886f12/1684322905.9627256/events.out.tfevents.1684322905.4e0a98886f12.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf902219034337dde3674230e2b319b9427170dbb2ae9e7abf715106e5fe6212
3
+ size 6110
runs/May17_11-28-15_4e0a98886f12/events.out.tfevents.1684322905.4e0a98886f12.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf713394d3dfa9071c4524dbaa9b4ee141d14ef1795fde90444d0863a8c131f8
3
+ size 9812
runs/May17_11-31-37_4e0a98886f12/1684323100.3542142/events.out.tfevents.1684323100.4e0a98886f12.31.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc7c4fee2f188095e7f5b7b77966bdd70f195142bb3172db83c167f45cb4477
3
+ size 6110
runs/May17_11-31-37_4e0a98886f12/events.out.tfevents.1684323100.4e0a98886f12.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dbc80f6fc80d7f18010dacfb1d338a70222461fc22219962ea64ce4b051c75
3
+ size 17532
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d415711f902130199574557cc354cc65dd6331dbfea11f02fb8b35dfb17c2866
3
+ size 3771