Hugging Face's logo

instilux
/
ltz-e1-base

Fill-Mask
Transformers
Safetensors
Luxembourgish
modernbert
encoder
luxembourgish
multilingual
masked-language-modeling
Model card Files
xet
 Community
fkoerner commited on
Commit
290b79c
·
verified ·
1 Parent(s): 6d6b929

Upload model and tokenizer files

Browse files
Files changed (5) hide show
  1. config.json +49 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +62 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "causal_mask": false,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 0,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "dtype": "float32",
17
+ "embedding_dropout": 0.0,
18
+ "eos_token_id": 1,
19
+ "global_attn_every_n_layers": 3,
20
+ "global_rope_theta": 160000.0,
21
+ "gradient_checkpointing": false,
22
+ "hidden_activation": "gelu",
23
+ "hidden_size": 768,
24
+ "initializer_cutoff_factor": 2.0,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 1152,
27
+ "layer_norm_eps": 1e-05,
28
+ "local_attention": 128,
29
+ "local_rope_theta": 160000.0,
30
+ "mask_token_id": 3,
31
+ "max_position_embeddings": 7999,
32
+ "mlp_bias": false,
33
+ "mlp_dropout": 0.0,
34
+ "model_max_length": 1024,
35
+ "model_type": "modernbert",
36
+ "norm_bias": false,
37
+ "norm_eps": 1e-05,
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 22,
40
+ "pad_token_id": 2,
41
+ "position_embedding_type": "sans_pos",
42
+ "repad_logits_with_grad": false,
43
+ "sep_token_id": 1,
44
+ "sparse_pred_ignore_index": -100,
45
+ "sparse_prediction": false,
46
+ "tokenizer_class": "GPTNeoXTokenizerFast",
47
+ "transformers_version": "4.57.0",
48
+ "vocab_size": 50368
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67bef4a9d450209513a85f787468b7d8e1dbdd3698dd2c1651c0cb39a6d8e2f
3
+ size 598635032
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "[CLS]",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "[SEP]",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "[PAD]",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "[MASK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "[UNK]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "bos_token": "[CLS]",
48
+ "clean_up_tokenization_spaces": true,
49
+ "cls_token": "[CLS]",
50
+ "eos_token": "[SEP]",
51
+ "extra_special_tokens": {},
52
+ "mask_token": "[MASK]",
53
+ "model_input_names": [
54
+ "input_ids",
55
+ "attention_mask"
56
+ ],
57
+ "model_max_length": 1024,
58
+ "pad_token": "[PAD]",
59
+ "sep_token": "[SEP]",
60
+ "tokenizer_class": "GPTNeoXTokenizer",
61
+ "unk_token": "[UNK]"
62
+ }