Hugging Face's logo

tirthadagr8
/
ViT_Bert_OCR-test

Safetensors
vision-encoder-decoder
Model card Files Community
tirthadagr8 commited on
Commit
0262043
·
verified ·
1 Parent(s): cd859be

Upload 17 files

Browse files
Files changed (17) hide show
  1. added_tokens.json +6 -0
  2. checkpoint-30000/config.json +178 -0
  3. checkpoint-30000/generation_config.json +12 -0
  4. checkpoint-30000/model.safetensors +3 -0
  5. checkpoint-30000/optimizer.pt +3 -0
  6. checkpoint-30000/rng_state.pth +3 -0
  7. checkpoint-30000/scheduler.pt +3 -0
  8. checkpoint-30000/trainer_state.json +0 -0
  9. checkpoint-30000/training_args.bin +3 -0
  10. config.json +178 -0
  11. generation_config.json +12 -0
  12. merges.txt +0 -0
  13. model.safetensors +3 -0
  14. special_tokens_map.json +30 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +55 -0
  17. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|bos|>": 12561,
3
+ "<|endoftext|>": 12563,
4
+ "<|eos|>": 12562,
5
+ "[PAD]": 12560
6
+ }
checkpoint-30000/config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/test_visionencoderdecoder/transformers/default/3/ocr-model/checkpoint-30000",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_attn_implementation_autoset": false,
8
+ "_name_or_path": "",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 12561,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 12562,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "min_length": 0,
48
+ "model_type": "bert",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 12,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 0,
59
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
68
+ "suppress_tokens": 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
+ "type_vocab_size": 2,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 12564
84
+ },
85
+ "decoder_start_token_id": 12561,
86
+ "early_stopping": null,
87
+ "encoder": {
88
+ "_attn_implementation_autoset": false,
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_probs_dropout_prob": 0.1,
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": 0.1,
111
+ "hidden_size": 768,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 224,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "is_training": true,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-06,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "vit",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_channels": 3,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": null,
142
+ "patch_attention": true,
143
+ "patch_size": 16,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "qkv_bias": true,
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false
166
+ },
167
+ "eos_token_id": 12562,
168
+ "is_encoder_decoder": true,
169
+ "length_penalty": null,
170
+ "max_length": null,
171
+ "model_type": "vision-encoder-decoder",
172
+ "no_repeat_ngram_size": null,
173
+ "num_beams": null,
174
+ "pad_token_id": 0,
175
+ "tie_word_embeddings": false,
176
+ "torch_dtype": "float32",
177
+ "transformers_version": "4.47.0"
178
+ }
checkpoint-30000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 12561,
4
+ "early_stopping": true,
5
+ "eos_token_id": 12562,
6
+ "length_penalty": 2.0,
7
+ "max_length": 64,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 5,
10
+ "pad_token_id": 0,
11
+ "transformers_version": "4.47.0"
12
+ }
checkpoint-30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea87220cce53f7c8e2ec8ed7318fc44ae9708ad250711d9f27861916b5a524d
3
+ size 841908112
checkpoint-30000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86304300b054a459dca023d0170255ecd5ab7d980b1e2515404866e26b9f638f
3
+ size 1679396714
checkpoint-30000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fa26d9606661b38e384cbbc22746beeee83fe7ce98768b8a2f552a1ae4bf05
3
+ size 14244
checkpoint-30000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b97e16245ed23f286cdeb91a60cb6fe806af6f24b2cc5468fefb313bb653b10
3
+ size 1064
checkpoint-30000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe6c752c38185156408a423c6d7800b92658b79c11d11cf1982155bdeb01bbb
3
+ size 5368
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/test_visionencoderdecoder/transformers/default/3/ocr-model/checkpoint-30000",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_attn_implementation_autoset": false,
8
+ "_name_or_path": "",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 12561,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 12562,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "min_length": 0,
48
+ "model_type": "bert",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 12,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 12,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 0,
59
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
68
+ "suppress_tokens": 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
+ "type_vocab_size": 2,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 12564
84
+ },
85
+ "decoder_start_token_id": 12561,
86
+ "early_stopping": null,
87
+ "encoder": {
88
+ "_attn_implementation_autoset": false,
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_probs_dropout_prob": 0.1,
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": 0.1,
111
+ "hidden_size": 768,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 224,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "is_training": true,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-06,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "vit",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_channels": 3,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": null,
142
+ "patch_attention": true,
143
+ "patch_size": 16,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "qkv_bias": true,
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false
166
+ },
167
+ "eos_token_id": 12562,
168
+ "is_encoder_decoder": true,
169
+ "length_penalty": null,
170
+ "max_length": null,
171
+ "model_type": "vision-encoder-decoder",
172
+ "no_repeat_ngram_size": null,
173
+ "num_beams": null,
174
+ "pad_token_id": 0,
175
+ "tie_word_embeddings": false,
176
+ "torch_dtype": "float32",
177
+ "transformers_version": "4.47.0"
178
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 12561,
4
+ "early_stopping": true,
5
+ "eos_token_id": 12562,
6
+ "length_penalty": 2.0,
7
+ "max_length": 64,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 5,
10
+ "pad_token_id": 0,
11
+ "transformers_version": "4.47.0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea87220cce53f7c8e2ec8ed7318fc44ae9708ad250711d9f27861916b5a524d
3
+ size 841908112
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|bos|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eos|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|pad|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "12560": {
15
+ "content": "[PAD]",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "12561": {
23
+ "content": "<|bos|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "12562": {
31
+ "content": "<|eos|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "12563": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "bos_token": "<|bos|>",
48
+ "clean_up_tokenization_spaces": false,
49
+ "eos_token": "<|eos|>",
50
+ "extra_special_tokens": {},
51
+ "model_max_length": 1024,
52
+ "pad_token": "<|pad|>",
53
+ "tokenizer_class": "GPT2Tokenizer",
54
+ "unk_token": "<|endoftext|>"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff