Hugging Face's logo

vatolinalex
/
scirus-modernbert-tiny-20m_epoch-2-step-982500

Safetensors
modernbert
Model card Files
xet
Community
vatolinalex commited on
Commit
8cd5c7a
·
verified ·
1 Parent(s): 15f4963

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. 1_Pooling/config.json +1 -0
  2. config.json +45 -0
  3. model.safetensors +3 -0
  4. modules.json +1 -0
  5. sentence_bert_config.json +1 -0
  6. special_tokens_map.json +37 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +73 -0
1_Pooling/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"word_embedding_dimension":312,"pooling_mode":"mean","pooling_mode_cls_token":false,"pooling_mode_mean_tokens":true,"pooling_mode_max_tokens":false,"pooling_mode_mean_sqrt_len_tokens":false}
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 3,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 1,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 10000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 312,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "local_attention": 128,
27
+ "local_rope_theta": 10000.0,
28
+ "max_position_embeddings": 8192,
29
+ "mlp_bias": false,
30
+ "mlp_dropout": 0.0,
31
+ "model_type": "modernbert",
32
+ "norm_bias": false,
33
+ "norm_eps": 1e-05,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 3,
36
+ "pad_token_id": 5,
37
+ "position_embedding_type": "absolute",
38
+ "repad_logits_with_grad": false,
39
+ "sep_token_id": 4,
40
+ "sparse_pred_ignore_index": -100,
41
+ "sparse_prediction": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.51.3",
44
+ "vocab_size": 50272
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26ef84cc595c792c719155b184bcd426a3e3985a5e378f22008d47000bfa11e
3
+ size 80361888
modules.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"idx":0,"name":"0","path":"","type":"sentence_transformers.models.Transformer"},{"idx":1,"name":"1","path":"1_Pooling","type":"sentence_transformers.models.Pooling"},{"idx":2,"name":"2","path":"2_Normalize","type":"sentence_transformers.models.Normalize"}]
sentence_bert_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"max_seq_length":8190,"do_lower_case":false}
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|padding|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[MASK]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "extra_special_tokens": {},
63
+ "mask_token": "[MASK]",
64
+ "model_input_names": [
65
+ "input_ids",
66
+ "attention_mask"
67
+ ],
68
+ "model_max_length": 8192,
69
+ "pad_token": "[PAD]",
70
+ "sep_token": "[SEP]",
71
+ "tokenizer_class": "PreTrainedTokenizer",
72
+ "unk_token": "[UNK]"
73
+ }