nielsr HF staff commited on
Commit
c329f13
1 Parent(s): 349ac8e

First commit

Browse files
config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "relu",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": 0.0,
16
+ "d_model": 1024,
17
+ "decoder_attention_heads": 16,
18
+ "decoder_ffn_dim": 4096,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 2,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.1,
25
+ "early_stopping": false,
26
+ "encoder_hidden_size": 1024,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 2,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layernorm_embedding": false,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 1024,
47
+ "min_length": 0,
48
+ "model_type": "trocr",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 1,
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "scale_embedding": true,
65
+ "sep_token_id": null,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": false,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torch_dtype": null,
74
+ "torchscript": false,
75
+ "transformers_version": "4.12.0.dev0",
76
+ "use_bfloat16": false,
77
+ "use_cache": false,
78
+ "use_learned_position_embeddings": false,
79
+ "vocab_size": 50265
80
+ },
81
+ "encoder": {
82
+ "_name_or_path": "",
83
+ "add_cross_attention": false,
84
+ "architectures": null,
85
+ "attention_probs_dropout_prob": 0.0,
86
+ "bad_words_ids": null,
87
+ "bos_token_id": null,
88
+ "chunk_size_feed_forward": 0,
89
+ "decoder_start_token_id": null,
90
+ "diversity_penalty": 0.0,
91
+ "do_sample": false,
92
+ "early_stopping": false,
93
+ "encoder_hidden_size": null,
94
+ "encoder_no_repeat_ngram_size": 0,
95
+ "eos_token_id": null,
96
+ "finetuning_task": null,
97
+ "forced_bos_token_id": null,
98
+ "forced_eos_token_id": null,
99
+ "hidden_act": "gelu",
100
+ "hidden_dropout_prob": 0.0,
101
+ "hidden_size": 1024,
102
+ "id2label": {
103
+ "0": "LABEL_0",
104
+ "1": "LABEL_1"
105
+ },
106
+ "image_size": 384,
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 4096,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "layer_norm_eps": 1e-12,
116
+ "length_penalty": 1.0,
117
+ "max_length": 20,
118
+ "min_length": 0,
119
+ "model_type": "vit",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 16,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_channels": 3,
125
+ "num_hidden_layers": 24,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": null,
131
+ "patch_size": 16,
132
+ "prefix": null,
133
+ "problem_type": null,
134
+ "pruned_heads": {},
135
+ "qkv_bias": false,
136
+ "remove_invalid_values": false,
137
+ "repetition_penalty": 1.0,
138
+ "return_dict": true,
139
+ "return_dict_in_generate": false,
140
+ "sep_token_id": null,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "transformers_version": "4.12.0.dev0",
151
+ "use_bfloat16": false
152
+ },
153
+ "is_encoder_decoder": true,
154
+ "model_type": "vision-encoder-decoder",
155
+ "tie_word_embeddings": false,
156
+ "torch_dtype": "float32",
157
+ "transformers_version": null
158
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:747198fc8a7368adc59f341b1ded2e9b0be3cbcc832df220c45813951cdc1ff2
3
+ size 2432726799
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/e16a2590deb9e6d73711d6e05bf27d832fa8c1162d807222e043ca650a556964.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff