Hugging Face's logo

breezedeus
/
pix2text-mfr-1.5

Image-to-Text
Transformers
ONNX
vision-encoder-decoder
image-text-to-text
latex-ocr
math-ocr
math-formula-recognition
mfr
pix2text
p2t
Model card Files
xet
 Community
breezedeus commited on
Commit
6e5376e
·
verified ·
1 Parent(s): 2772c9b

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +60 -0
  2. decoder_model.onnx +3 -0
  3. encoder_model.onnx +3 -0
  4. generation_config.json +10 -0
  5. preprocessor_config.json +28 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +56 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "activation_dropout": 0.0,
7
+ "activation_function": "relu",
8
+ "add_cross_attention": true,
9
+ "attention_dropout": 0.0,
10
+ "classifier_dropout": 0.0,
11
+ "cross_attention_hidden_size": 384,
12
+ "d_model": 256,
13
+ "decoder_attention_heads": 8,
14
+ "decoder_ffn_dim": 1024,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 6,
17
+ "dropout": 0.1,
18
+ "init_std": 0.02,
19
+ "is_decoder": true,
20
+ "layernorm_embedding": true,
21
+ "max_position_embeddings": 1024,
22
+ "model_type": "trocr",
23
+ "scale_embedding": true,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "use_cache": false,
27
+ "use_learned_position_embeddings": true,
28
+ "vocab_size": 1868
29
+ },
30
+ "decoder_start_token_id": 1,
31
+ "encoder": {
32
+ "attention_probs_dropout_prob": 0.0,
33
+ "encoder_stride": 16,
34
+ "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.0,
36
+ "hidden_size": 384,
37
+ "image_size": 384,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 1536,
40
+ "layer_norm_eps": 1e-12,
41
+ "model_type": "deit",
42
+ "num_attention_heads": 6,
43
+ "num_channels": 3,
44
+ "num_hidden_layers": 12,
45
+ "patch_size": 16,
46
+ "pooler_act": "tanh",
47
+ "pooler_output_size": 384,
48
+ "qkv_bias": true,
49
+ "torch_dtype": "float32"
50
+ },
51
+ "eos_token_id": 2,
52
+ "is_encoder_decoder": true,
53
+ "model_type": "vision-encoder-decoder",
54
+ "pad_token_id": 0,
55
+ "tie_word_embeddings": false,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.52.3",
58
+ "use_cache": false,
59
+ "vocab_size": 1868
60
+ }
decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917deb98e91a0453c5f234f58a0f32f9fb037de8527c7eb4ed394daf9e692f2a
3
+ size 32026253
encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080a3f660f08bc9ebcacdd96e34be6b6400f8c7e62d7cd0dd8251badc37f610b
3
+ size 87510770
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "max_new_tokens": 1024,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.52.3",
9
+ "use_cache": false
10
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": false,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "DeiTImageProcessor",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "processor_class": "TrOCRProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "height": 384,
26
+ "width": 384
27
+ }
28
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "processor_class": "TrOCRProcessor",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "XLMRobertaTokenizerFast",
55
+ "unk_token": "<unk>"
56
+ }