HugoSchtr commited on
Commit
a381619
1 Parent(s): 4a020b6

Upload model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ xlm-roberta-large-ehri-ner-all/tokenizer.json filter=lfs diff=lfs merge=lfs -text
xlm-roberta-large-ehri-ner-all/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "B-CAMP",
15
+ "1": "B-DATE",
16
+ "2": "B-GHETTO",
17
+ "3": "B-LOC",
18
+ "4": "B-ORG",
19
+ "5": "B-PERS",
20
+ "6": "I-CAMP",
21
+ "7": "I-DATE",
22
+ "8": "I-GHETTO",
23
+ "9": "I-LOC",
24
+ "10": "I-ORG",
25
+ "11": "I-PERS",
26
+ "12": "O"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 4096,
30
+ "label2id": {
31
+ "B-CAMP": 0,
32
+ "B-DATE": 1,
33
+ "B-GHETTO": 2,
34
+ "B-LOC": 3,
35
+ "B-ORG": 4,
36
+ "B-PERS": 5,
37
+ "I-CAMP": 6,
38
+ "I-DATE": 7,
39
+ "I-GHETTO": 8,
40
+ "I-LOC": 9,
41
+ "I-ORG": 10,
42
+ "I-PERS": 11,
43
+ "O": 12
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "xlm-roberta",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 24,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.38.1",
55
+ "type_vocab_size": 1,
56
+ "use_cache": true,
57
+ "vocab_size": 250002
58
+ }
xlm-roberta-large-ehri-ner-all/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d573836293b30df6702087975332e0d71f05dd3830aeaf773f37238d54b08353
3
+ size 2235465156
xlm-roberta-large-ehri-ner-all/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
+ }
xlm-roberta-large-ehri-ner-all/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
3
+ size 17082854
xlm-roberta-large-ehri-ner-all/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
xlm-roberta-large-ehri-ner-all/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6129bba07f6db498da456dc9184262bffc85cc972e2e467a609340a8fcb9fa2
3
+ size 4856