vrashad commited on
Commit
e50ac1b
·
verified ·
1 Parent(s): 37f1f76

Upload mmBERT-base truncated to EN+AZ vocabulary (71K tokens)

Browse files
Files changed (4) hide show
  1. config.json +78 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +24 -0
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
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
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "layer_types": [
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention"
49
+ ],
50
+ "local_attention": 128,
51
+ "mask_token_id": 4,
52
+ "max_position_embeddings": 8192,
53
+ "mlp_bias": false,
54
+ "mlp_dropout": 0.0,
55
+ "model_type": "modernbert",
56
+ "norm_bias": false,
57
+ "norm_eps": 1e-05,
58
+ "num_attention_heads": 6,
59
+ "num_hidden_layers": 22,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "sans_pos",
62
+ "rope_parameters": {
63
+ "full_attention": {
64
+ "rope_theta": 160000,
65
+ "rope_type": "default"
66
+ },
67
+ "sliding_attention": {
68
+ "rope_theta": 160000,
69
+ "rope_type": "default"
70
+ }
71
+ },
72
+ "sep_token_id": 1,
73
+ "sparse_pred_ignore_index": -100,
74
+ "sparse_prediction": false,
75
+ "tie_word_embeddings": true,
76
+ "transformers_version": "5.3.0",
77
+ "vocab_size": 71751
78
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad64e004cd39eac1c51f1594b9baeb908c60ad39d4886a4e2063eb5d7c5b208
3
+ size 278981368
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }