Commit
•
1323537
1
Parent(s):
eb4f066
Upload 9 files
Browse files- config.json +178 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +37 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./Caroline",
|
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": 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 |
+
"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": 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 |
+
"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": 768,
|
112 |
+
"id2label": {
|
113 |
+
"0": "LABEL_0",
|
114 |
+
"1": "LABEL_1"
|
115 |
+
},
|
116 |
+
"image_size": 384,
|
117 |
+
"initializer_range": 0.02,
|
118 |
+
"intermediate_size": 3072,
|
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": 12,
|
132 |
+
"num_beam_groups": 1,
|
133 |
+
"num_beams": 1,
|
134 |
+
"num_channels": 3,
|
135 |
+
"num_hidden_layers": 12,
|
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": 64,
|
169 |
+
"model_type": "vision-encoder-decoder",
|
170 |
+
"no_repeat_ngram_size": 3,
|
171 |
+
"num_beams": 4,
|
172 |
+
"pad_token_id": 1,
|
173 |
+
"processor_class": "TrOCRProcessor",
|
174 |
+
"tie_word_embeddings": false,
|
175 |
+
"torch_dtype": "float32",
|
176 |
+
"transformers_version": "4.39.3",
|
177 |
+
"vocab_size": 50265
|
178 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.39.3",
|
8 |
+
"use_cache": false
|
9 |
+
}
|
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 sha256:524e6256d7931edcfeb0e4deb96d174232875a4813b04b0b13304403070792a2
|
3 |
+
size 1335747032
|
preprocessor_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTImageProcessor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"processor_class": "TrOCRProcessor",
|
31 |
+
"resample": 2,
|
32 |
+
"rescale_factor": 0.00392156862745098,
|
33 |
+
"size": {
|
34 |
+
"height": 384,
|
35 |
+
"width": 384
|
36 |
+
}
|
37 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 128,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"processor_class": "TrOCRProcessor",
|
58 |
+
"sep_token": "</s>",
|
59 |
+
"stride": 0,
|
60 |
+
"tokenizer_class": "RobertaTokenizer",
|
61 |
+
"trim_offsets": true,
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
+
"unk_token": "<unk>"
|
65 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|