Commit
·
616f00f
1
Parent(s):
232dd3d
Upload 7 files
Browse files- config.json +14 -7
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +13 -5
- tokenizer.json +0 -0
- tokenizer_config.json +11 -17
- vocab.json +0 -0
config.json
CHANGED
@@ -1,26 +1,33 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LayoutLMForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
|
|
|
|
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 3072,
|
12 |
-
"layer_norm_eps": 1e-
|
13 |
"max_2d_position_embeddings": 1024,
|
14 |
-
"max_position_embeddings":
|
15 |
"model_type": "layoutlm",
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
-
"
|
19 |
-
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.33.2",
|
23 |
-
"type_vocab_size":
|
24 |
"use_cache": true,
|
25 |
-
"vocab_size":
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "magorshunov/layoutlm-invoices",
|
3 |
"architectures": [
|
4 |
"LayoutLMForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
"hidden_size": 768,
|
14 |
"initializer_range": 0.02,
|
15 |
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
"max_2d_position_embeddings": 1024,
|
18 |
+
"max_position_embeddings": 514,
|
19 |
"model_type": "layoutlm",
|
20 |
"num_attention_heads": 12,
|
21 |
"num_hidden_layers": 12,
|
22 |
+
"pad_token_id": 1,
|
|
|
23 |
"position_embedding_type": "absolute",
|
24 |
+
"token_classification": true,
|
25 |
+
"token_classifier_constant": 0.1,
|
26 |
+
"token_classifier_reduction": "sum",
|
27 |
+
"tokenizer_class": "RobertaTokenizer",
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.33.2",
|
30 |
+
"type_vocab_size": 1,
|
31 |
"use_cache": true,
|
32 |
+
"vocab_size": 50265
|
33 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3183a7ed7e973772f7b44c3606c7b9413288714b01d989be170d3a784e479f72
|
3 |
+
size 511248969
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,21 +1,15 @@
|
|
1 |
{
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
-
"cls_token": "
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"max_length": 512,
|
8 |
"model_max_length": 512,
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"stride": 0,
|
15 |
-
"strip_accents": null,
|
16 |
-
"tokenize_chinese_chars": true,
|
17 |
-
"tokenizer_class": "LayoutLMTokenizer",
|
18 |
-
"truncation_side": "right",
|
19 |
-
"truncation_strategy": "only_second",
|
20 |
-
"unk_token": "[UNK]"
|
21 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
|
|
9 |
"model_max_length": 512,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"tokenizer_class": "RobertaTokenizer",
|
13 |
+
"trim_offsets": true,
|
14 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|