Hugging Face's logo

niharrp9
/
distilbert-base-multilingual-cased-finetuned-language-identification

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
niharrp9 commited on
Commit
d7f3c8c
•
1 Parent(s): b00d0ba

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +70 -0
  2. model.safetensors +3 -0
  3. runs/Oct31_15-04-23_654dc69d4b43/events.out.tfevents.1730387076.654dc69d4b43.3701.0 +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_10": 10,
38
+ "LABEL_11": 11,
39
+ "LABEL_12": 12,
40
+ "LABEL_13": 13,
41
+ "LABEL_14": 14,
42
+ "LABEL_15": 15,
43
+ "LABEL_16": 16,
44
+ "LABEL_17": 17,
45
+ "LABEL_18": 18,
46
+ "LABEL_19": 19,
47
+ "LABEL_2": 2,
48
+ "LABEL_3": 3,
49
+ "LABEL_4": 4,
50
+ "LABEL_5": 5,
51
+ "LABEL_6": 6,
52
+ "LABEL_7": 7,
53
+ "LABEL_8": 8,
54
+ "LABEL_9": 9
55
+ },
56
+ "max_position_embeddings": 512,
57
+ "model_type": "distilbert",
58
+ "n_heads": 12,
59
+ "n_layers": 6,
60
+ "output_past": true,
61
+ "pad_token_id": 0,
62
+ "problem_type": "single_label_classification",
63
+ "qa_dropout": 0.1,
64
+ "seq_classif_dropout": 0.2,
65
+ "sinusoidal_pos_embds": false,
66
+ "tie_weights_": true,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.46.1",
69
+ "vocab_size": 119547
70
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1cc865760cc70fa7062f7535f3c6e00ef70f242b6f23a393c2e9a629b67885
3
+ size 541372744
runs/Oct31_15-04-23_654dc69d4b43/events.out.tfevents.1730387076.654dc69d4b43.3701.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d388d73e272a398f2d9591b28f9b0d107b6edbe57b248b32227bfa8f03876426
3
+ size 5956
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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341eaeb1c12d50bd74c651b0778b00db75c183dbd8a62ba02c70da5ccbd970a9
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff