ngupta2026 commited on
Commit
beebac8
·
verified ·
1 Parent(s): ac1fb86

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +16 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LayoutLMForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "COMPANY",
15
+ "2": "DATE",
16
+ "3": "TOTAL"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "COMPANY": 1,
22
+ "DATE": 2,
23
+ "O": 0,
24
+ "TOTAL": 3
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_2d_position_embeddings": 1024,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "layoutlm",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "5.6.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980f25570b027a63d1df52ee86a2b2e25873a0d460f0a2bf73c4b2d09f05970e
3
+ size 450548984
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_len": 512,
9
+ "model_max_length": 512,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }