Update tiny models for LayoutLMv3Model
Browse files- config.json +38 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +36 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LayoutLMv3Model"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"coordinate_size": 6,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"has_relative_attention_bias": true,
|
| 12 |
+
"has_spatial_attention_bias": true,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 36,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"input_size": 4,
|
| 18 |
+
"intermediate_size": 37,
|
| 19 |
+
"layer_norm_eps": 1e-05,
|
| 20 |
+
"max_2d_position_embeddings": 1024,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"max_rel_2d_pos": 256,
|
| 23 |
+
"max_rel_pos": 128,
|
| 24 |
+
"model_type": "layoutlmv3",
|
| 25 |
+
"num_attention_heads": 4,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 2,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"patch_size": 2,
|
| 30 |
+
"rel_2d_pos_bins": 64,
|
| 31 |
+
"rel_pos_bins": 32,
|
| 32 |
+
"shape_size": 6,
|
| 33 |
+
"text_embed": true,
|
| 34 |
+
"transformers_version": "5.16.0.dev0",
|
| 35 |
+
"type_vocab_size": 16,
|
| 36 |
+
"visual_embed": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5ed90a835036215f748fd3783333dfa60451c5ce4acaf24b8a68ab421facaaa
|
| 3 |
+
size 7489608
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": true,
|
| 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": "LayoutLMv3ImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
},
|
| 23 |
+
"tesseract_config": ""
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"cls_token_box": [
|
| 7 |
+
0,
|
| 8 |
+
0,
|
| 9 |
+
0,
|
| 10 |
+
0
|
| 11 |
+
],
|
| 12 |
+
"eos_token": "</s>",
|
| 13 |
+
"errors": "replace",
|
| 14 |
+
"is_local": true,
|
| 15 |
+
"local_files_only": false,
|
| 16 |
+
"mask_token": "<mask>",
|
| 17 |
+
"model_max_length": 512,
|
| 18 |
+
"only_label_first_subword": true,
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"pad_token_box": [
|
| 21 |
+
0,
|
| 22 |
+
0,
|
| 23 |
+
0,
|
| 24 |
+
0
|
| 25 |
+
],
|
| 26 |
+
"pad_token_label": -100,
|
| 27 |
+
"sep_token": "</s>",
|
| 28 |
+
"sep_token_box": [
|
| 29 |
+
0,
|
| 30 |
+
0,
|
| 31 |
+
0,
|
| 32 |
+
0
|
| 33 |
+
],
|
| 34 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
| 35 |
+
"unk_token": "<unk>"
|
| 36 |
+
}
|