Hugging Face's logo

imperiusrex
/
Handwritten-model

Model card Files Community
imperiusrex commited on
Commit
58264ba
·
verified ·
1 Parent(s): 8717979

Upload 9 files

Browse files
Files changed (9) hide show
  1. local_trocr_model/config.json +54 -0
  2. local_trocr_model/generation_config.json +9 -0
  3. local_trocr_model/merges.txt +0 -0
  4. local_trocr_model/model-001.safetensors +3 -0
  5. local_trocr_model/preprocessor_config.json +24 -0
  6. local_trocr_model/special_tokens_map.json +51 -0
  7. local_trocr_model/tokenizer.json +0 -0
  8. local_trocr_model/tokenizer_config.json +59 -0
  9. local_trocr_model/vocab.json +0 -0
local_trocr_model/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "activation_dropout": 0.0,
7
+ "activation_function": "gelu",
8
+ "add_cross_attention": true,
9
+ "attention_dropout": 0.0,
10
+ "classifier_dropout": 0.0,
11
+ "cross_attention_hidden_size": 1024,
12
+ "d_model": 1024,
13
+ "decoder_attention_heads": 16,
14
+ "decoder_ffn_dim": 4096,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 12,
17
+ "dropout": 0.1,
18
+ "init_std": 0.02,
19
+ "is_decoder": true,
20
+ "layernorm_embedding": true,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "trocr",
23
+ "scale_embedding": false,
24
+ "torch_dtype": "float32",
25
+ "use_cache": false,
26
+ "use_learned_position_embeddings": true,
27
+ "vocab_size": 50265
28
+ },
29
+ "encoder": {
30
+ "attention_probs_dropout_prob": 0.0,
31
+ "encoder_stride": 16,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.0,
34
+ "hidden_size": 1024,
35
+ "image_size": 384,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 4096,
38
+ "layer_norm_eps": 1e-12,
39
+ "model_type": "vit",
40
+ "num_attention_heads": 16,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 24,
43
+ "patch_size": 16,
44
+ "pooler_act": "tanh",
45
+ "pooler_output_size": 1024,
46
+ "qkv_bias": false,
47
+ "torch_dtype": "float32"
48
+ },
49
+ "is_encoder_decoder": true,
50
+ "model_type": "vision-encoder-decoder",
51
+ "tie_word_embeddings": false,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.53.3"
54
+ }
local_trocr_model/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": "4.53.3",
8
+ "use_cache": false
9
+ }
local_trocr_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
local_trocr_model/model-001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afb64e0ac3c678e17df70e5683fb1822c8a0636ac80cf0f452d14e93929bd23
3
+ size 2232985336
local_trocr_model/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "TrOCRProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 384,
22
+ "width": 384
23
+ }
24
+ }
local_trocr_model/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
+ }
local_trocr_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
local_trocr_model/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "processor_class": "TrOCRProcessor",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
59
+ }
local_trocr_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff