Hugging Face's logo

kanansharmaa
/
layoutlmv2_finetuned_docvqa

Document Question Answering
Transformers
TensorBoard
Safetensors
layoutlmv2
Inference Endpoints
Model card Files Metrics Community
kanansharmaa commited on
Commit
cfb3882
•
1 Parent(s): 1e866e5

Training in progress, step 200

Browse files
Files changed (10) hide show
  1. config.json +132 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +25 -0
  4. runs/Apr29_12-50-02_innobit-Z390-M/events.out.tfevents.1714375220.innobit-Z390-M.445334.0 +3 -0
  5. runs/Apr29_14-46-18_innobit-Z390-M/events.out.tfevents.1714382182.innobit-Z390-M.470718.0 +3 -0
  6. special_tokens_map.json +37 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +79 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ml/Kanan/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "convert_sync_batchnorm": true,
8
+ "coordinate_size": 128,
9
+ "detectron2_config_args": {
10
+ "MODEL.ANCHOR_GENERATOR.SIZES": [
11
+ [
12
+ 32
13
+ ],
14
+ [
15
+ 64
16
+ ],
17
+ [
18
+ 128
19
+ ],
20
+ [
21
+ 256
22
+ ],
23
+ [
24
+ 512
25
+ ]
26
+ ],
27
+ "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
28
+ "MODEL.FPN.IN_FEATURES": [
29
+ "res2",
30
+ "res3",
31
+ "res4",
32
+ "res5"
33
+ ],
34
+ "MODEL.MASK_ON": true,
35
+ "MODEL.PIXEL_STD": [
36
+ 57.375,
37
+ 57.12,
38
+ 58.395
39
+ ],
40
+ "MODEL.POST_NMS_TOPK_TEST": 1000,
41
+ "MODEL.RESNETS.ASPECT_RATIOS": [
42
+ [
43
+ 0.5,
44
+ 1.0,
45
+ 2.0
46
+ ]
47
+ ],
48
+ "MODEL.RESNETS.DEPTH": 101,
49
+ "MODEL.RESNETS.NUM_GROUPS": 32,
50
+ "MODEL.RESNETS.OUT_FEATURES": [
51
+ "res2",
52
+ "res3",
53
+ "res4",
54
+ "res5"
55
+ ],
56
+ "MODEL.RESNETS.SIZES": [
57
+ [
58
+ 32
59
+ ],
60
+ [
61
+ 64
62
+ ],
63
+ [
64
+ 128
65
+ ],
66
+ [
67
+ 256
68
+ ],
69
+ [
70
+ 512
71
+ ]
72
+ ],
73
+ "MODEL.RESNETS.STRIDE_IN_1X1": false,
74
+ "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
75
+ "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
76
+ "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
77
+ "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
78
+ "MODEL.ROI_HEADS.IN_FEATURES": [
79
+ "p2",
80
+ "p3",
81
+ "p4",
82
+ "p5"
83
+ ],
84
+ "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
85
+ "MODEL.ROI_HEADS.NUM_CLASSES": 5,
86
+ "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
87
+ "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
88
+ "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
89
+ "MODEL.RPN.IN_FEATURES": [
90
+ "p2",
91
+ "p3",
92
+ "p4",
93
+ "p5",
94
+ "p6"
95
+ ],
96
+ "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
97
+ "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
98
+ "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
99
+ },
100
+ "fast_qkv": true,
101
+ "gradient_checkpointing": false,
102
+ "has_relative_attention_bias": true,
103
+ "has_spatial_attention_bias": true,
104
+ "has_visual_segment_embedding": true,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "image_feature_pool_shape": [
109
+ 7,
110
+ 7,
111
+ 256
112
+ ],
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "layer_norm_eps": 1e-12,
116
+ "max_2d_position_embeddings": 1024,
117
+ "max_position_embeddings": 512,
118
+ "max_rel_2d_pos": 256,
119
+ "max_rel_pos": 128,
120
+ "model_type": "layoutlmv2",
121
+ "num_attention_heads": 12,
122
+ "num_hidden_layers": 12,
123
+ "output_past": true,
124
+ "pad_token_id": 0,
125
+ "rel_2d_pos_bins": 64,
126
+ "rel_pos_bins": 32,
127
+ "shape_size": 128,
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.39.3",
130
+ "type_vocab_size": 2,
131
+ "vocab_size": 30522
132
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63b5807b724123a785ec7e04fc68068997d999989620d6c577e15b14a6798b0
3
+ size 802053752
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "apply_ocr",
8
+ "ocr_lang",
9
+ "tesseract_config",
10
+ "return_tensors",
11
+ "data_format",
12
+ "input_data_format"
13
+ ],
14
+ "apply_ocr": true,
15
+ "do_resize": true,
16
+ "image_processor_type": "LayoutLMv2ImageProcessor",
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv2Processor",
19
+ "resample": 2,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ }
runs/Apr29_12-50-02_innobit-Z390-M/events.out.tfevents.1714375220.innobit-Z390-M.445334.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f239a9145f46cdd3d155dd2bccd1b1956dc116dca6c5a8396202181c6af987a3
3
+ size 4996
runs/Apr29_14-46-18_innobit-Z390-M/events.out.tfevents.1714382182.innobit-Z390-M.470718.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70962b872f33d179502462210344f75589572998da4a1334a799ad78b726c384
3
+ size 8604
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
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": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "cls_token_box": [
48
+ 0,
49
+ 0,
50
+ 0,
51
+ 0
52
+ ],
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "never_split": null,
58
+ "only_label_first_subword": true,
59
+ "pad_token": "[PAD]",
60
+ "pad_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "pad_token_label": -100,
67
+ "processor_class": "LayoutLMv2Processor",
68
+ "sep_token": "[SEP]",
69
+ "sep_token_box": [
70
+ 1000,
71
+ 1000,
72
+ 1000,
73
+ 1000
74
+ ],
75
+ "strip_accents": null,
76
+ "tokenize_chinese_chars": true,
77
+ "tokenizer_class": "LayoutLMv2Tokenizer",
78
+ "unk_token": "[UNK]"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fafdd3c33c00cec7a76fa03637d7971f10ff1cb7d031fd05acde21908bf3c2
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff