MatteoFasulo commited on
Commit
eaf6088
·
verified ·
1 Parent(s): df067f2

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +100 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +16 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": null,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "O",
24
+ "1": "B-PER",
25
+ "2": "I-PER",
26
+ "3": "B-ORG",
27
+ "4": "I-ORG",
28
+ "5": "B-LOC",
29
+ "6": "I-LOC",
30
+ "7": "B-MISC",
31
+ "8": "I-MISC"
32
+ },
33
+ "initializer_cutoff_factor": 2.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 1152,
36
+ "label2id": {
37
+ "B-LOC": 5,
38
+ "B-MISC": 7,
39
+ "B-ORG": 3,
40
+ "B-PER": 1,
41
+ "I-LOC": 6,
42
+ "I-MISC": 8,
43
+ "I-ORG": 4,
44
+ "I-PER": 2,
45
+ "O": 0
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "layer_types": [
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention"
71
+ ],
72
+ "local_attention": 128,
73
+ "max_position_embeddings": 8192,
74
+ "mlp_bias": false,
75
+ "mlp_dropout": 0.0,
76
+ "model_type": "modernbert",
77
+ "norm_bias": false,
78
+ "norm_eps": 1e-05,
79
+ "num_attention_heads": 12,
80
+ "num_hidden_layers": 22,
81
+ "pad_token_id": 50283,
82
+ "position_embedding_type": "absolute",
83
+ "rope_parameters": {
84
+ "full_attention": {
85
+ "rope_theta": 160000.0,
86
+ "rope_type": "default"
87
+ },
88
+ "sliding_attention": {
89
+ "rope_theta": 10000.0,
90
+ "rope_type": "default"
91
+ }
92
+ },
93
+ "sep_token_id": 50282,
94
+ "sparse_pred_ignore_index": -100,
95
+ "sparse_prediction": false,
96
+ "tie_word_embeddings": true,
97
+ "transformers_version": "5.1.0",
98
+ "use_cache": false,
99
+ "vocab_size": 50368
100
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24126599cee54634556a2b5aa388bf1a2e93471e4081bf8a10c1b4b258a4444
3
+ size 598461316
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a2c53ff6b6c3b366bb2e822f634049ba0caa38bcfd29d0ba005bfa92db2715
3
+ size 4728