Hugging Face's logo

jaewon0916
/
xlm-roberta-base-finetuned-panx-de-fr

Token Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
jaewon0916 commited on
Commit
d408aca
•
1 Parent(s): 6b0f417

Training in progress, step 2145

Browse files
Files changed (7) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +55 -0
  6. training_args.bin +3 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
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": 768,
13
+ "id2label": {
14
+ "-100": "IGN",
15
+ "0": "O",
16
+ "1": "B-PER",
17
+ "2": "I-PER",
18
+ "3": "B-ORG",
19
+ "4": "I-ORG",
20
+ "5": "B-LOC",
21
+ "6": "I-LOC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 5,
27
+ "B-ORG": 3,
28
+ "B-PER": 1,
29
+ "I-LOC": 6,
30
+ "I-ORG": 4,
31
+ "I-PER": 2,
32
+ "O": 0
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 514,
36
+ "model_type": "xlm-roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "output_past": true,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.46.2",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6dd19125249633fa95b40b0efcd77fab79ef7716e40c64a7af54e7b7260aa9
3
+ size 1109860880
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5276296863be900390667e76c91d07d5098036ebf575589318275c564a5738c
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff