Hugging Face's logo

drajend9
/
longformer-base-4096-ner-accelerate-invoice

Safetensors
longformer
Model card Files Community
drajend9 commited on
Commit
892ed01
•
1 Parent(s): 55c8d66

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. config.json +93 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForTokenClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "O",
30
+ "1": "B-BUY_G",
31
+ "2": "B-BUY_N",
32
+ "3": "B-GSTL",
33
+ "4": "B-GT_AMT",
34
+ "5": "B-GT_AMTL",
35
+ "6": "B-INV_DL",
36
+ "7": "B-INV_DT",
37
+ "8": "B-INV_L",
38
+ "9": "B-INV_NO",
39
+ "10": "B-SUPP_G",
40
+ "11": "B-SUPP_N",
41
+ "12": "I-BUY_G",
42
+ "13": "I-BUY_N",
43
+ "14": "I-GSTL",
44
+ "15": "I-GT_AMT",
45
+ "16": "I-GT_AMTL",
46
+ "17": "I-INV_DL",
47
+ "18": "I-INV_DT",
48
+ "19": "I-INV_L",
49
+ "20": "I-INV_NO",
50
+ "21": "I-SUPP_G",
51
+ "22": "I-SUPP_N"
52
+ },
53
+ "ignore_attention_mask": false,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "label2id": {
57
+ "B-BUY_G": 1,
58
+ "B-BUY_N": 2,
59
+ "B-GSTL": 3,
60
+ "B-GT_AMT": 4,
61
+ "B-GT_AMTL": 5,
62
+ "B-INV_DL": 6,
63
+ "B-INV_DT": 7,
64
+ "B-INV_L": 8,
65
+ "B-INV_NO": 9,
66
+ "B-SUPP_G": 10,
67
+ "B-SUPP_N": 11,
68
+ "I-BUY_G": 12,
69
+ "I-BUY_N": 13,
70
+ "I-GSTL": 14,
71
+ "I-GT_AMT": 15,
72
+ "I-GT_AMTL": 16,
73
+ "I-INV_DL": 17,
74
+ "I-INV_DT": 18,
75
+ "I-INV_L": 19,
76
+ "I-INV_NO": 20,
77
+ "I-SUPP_G": 21,
78
+ "I-SUPP_N": 22,
79
+ "O": 0
80
+ },
81
+ "layer_norm_eps": 1e-05,
82
+ "max_position_embeddings": 4098,
83
+ "model_type": "longformer",
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "onnx_export": false,
87
+ "pad_token_id": 1,
88
+ "sep_token_id": 2,
89
+ "torch_dtype": "float32",
90
+ "transformers_version": "4.42.3",
91
+ "type_vocab_size": 1,
92
+ "vocab_size": 50265
93
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16b20e901f232db09f89084fe45d3d791f53f0f194c1b795e4134cecb2c6269
3
+ size 592380196
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff