chiennv commited on
Commit
099875e
·
verified ·
1 Parent(s): 96d250d

Upload folder using huggingface_hub

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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 1,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 384,
22
+ "id2label": {
23
+ "0": "ko",
24
+ "1": "no",
25
+ "2": "da",
26
+ "3": "sv",
27
+ "4": "fi",
28
+ "5": "nl",
29
+ "6": "en",
30
+ "7": "fr",
31
+ "8": "de",
32
+ "9": "es",
33
+ "10": "pt",
34
+ "11": "it",
35
+ "12": "ja",
36
+ "13": "UNKNOWN"
37
+ },
38
+ "initializer_cutoff_factor": 2.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 1152,
41
+ "label2id": {
42
+ "UNKNOWN": 13,
43
+ "da": 2,
44
+ "de": 8,
45
+ "en": 6,
46
+ "es": 9,
47
+ "fi": 4,
48
+ "fr": 7,
49
+ "it": 11,
50
+ "ja": 12,
51
+ "ko": 0,
52
+ "nl": 5,
53
+ "no": 1,
54
+ "pt": 10,
55
+ "sv": 3
56
+ },
57
+ "layer_norm_eps": 1e-05,
58
+ "layer_types": [
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "full_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "full_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "full_attention"
81
+ ],
82
+ "local_attention": 128,
83
+ "mask_token_id": 4,
84
+ "max_position_embeddings": 8192,
85
+ "mlp_bias": false,
86
+ "mlp_dropout": 0.0,
87
+ "model_type": "modernbert",
88
+ "norm_bias": false,
89
+ "norm_eps": 1e-05,
90
+ "num_attention_heads": 6,
91
+ "num_hidden_layers": 22,
92
+ "pad_token_id": 0,
93
+ "position_embedding_type": "sans_pos",
94
+ "problem_type": "single_label_classification",
95
+ "rope_parameters": {
96
+ "full_attention": {
97
+ "rope_theta": 160000,
98
+ "rope_type": "default"
99
+ },
100
+ "sliding_attention": {
101
+ "rope_theta": 160000,
102
+ "rope_type": "default"
103
+ }
104
+ },
105
+ "sep_token_id": 1,
106
+ "sparse_pred_ignore_index": -100,
107
+ "sparse_prediction": false,
108
+ "tie_word_embeddings": true,
109
+ "transformers_version": "5.3.0",
110
+ "use_cache": false,
111
+ "vocab_size": 256000
112
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce09b8b2a7d2f2017f33b48b98df0723c7e5b4160932cd503807cbf54ef66720
3
+ size 562601880
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
3
+ size 34363188
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "cls_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "extra_special_tokens": [
8
+ "<start_of_turn>",
9
+ "<end_of_turn>"
10
+ ],
11
+ "is_local": false,
12
+ "mask_token": "<mask>",
13
+ "model_input_names": [
14
+ "input_ids",
15
+ "attention_mask"
16
+ ],
17
+ "model_max_length": 8192,
18
+ "pad_token": "<pad>",
19
+ "padding_side": "right",
20
+ "sep_token": "<eos>",
21
+ "spaces_between_special_tokens": false,
22
+ "tokenizer_class": "TokenizersBackend",
23
+ "unk_token": "<unk>"
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41301c77cefd849e7c6bc4c083daa5c38d86248dbba5da37f76ab99de4513500
3
+ size 5201