Hugging Face's logo

erickdp
/
sentiment-mrbert

Safetensors
xlm-roberta
Model card Files
xet
 Community
erickdp commited on
Commit
9cc6e7a
·
verified ·
1 Parent(s): 7cd06f3

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +90 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +21 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 0,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 2,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "NEGATIVE",
24
+ "1": "NEUTRAL",
25
+ "2": "POSITIVE"
26
+ },
27
+ "initializer_cutoff_factor": 2.0,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 1152,
30
+ "label2id": {
31
+ "NEGATIVE": 0,
32
+ "NEUTRAL": 1,
33
+ "POSITIVE": 2
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "layer_types": [
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
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
+ ],
60
+ "local_attention": 128,
61
+ "max_position_embeddings": 8192,
62
+ "mlp_bias": false,
63
+ "mlp_dropout": 0.0,
64
+ "model_type": "modernbert",
65
+ "norm_bias": false,
66
+ "norm_eps": 1e-05,
67
+ "num_attention_heads": 12,
68
+ "num_hidden_layers": 22,
69
+ "pad_token_id": 1,
70
+ "position_embedding_type": "absolute",
71
+ "problem_type": "single_label_classification",
72
+ "repad_logits_with_grad": false,
73
+ "rope_parameters": {
74
+ "full_attention": {
75
+ "rope_theta": 160000.0,
76
+ "rope_type": "default"
77
+ },
78
+ "sliding_attention": {
79
+ "rope_theta": 10000.0,
80
+ "rope_type": "default"
81
+ }
82
+ },
83
+ "sep_token_id": 2,
84
+ "sparse_pred_ignore_index": -100,
85
+ "sparse_prediction": false,
86
+ "tie_word_embeddings": true,
87
+ "transformers_version": "5.5.4",
88
+ "use_cache": false,
89
+ "vocab_size": 51200
90
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41def85f46c6c7241faa2b2e0309178d6f1a0eb3835513cb422488ddcca2feaf
3
+ size 600998764
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": true,
9
+ "mask_token": "<mask>",
10
+ "model_input_names": [
11
+ "input_ids",
12
+ "attention_mask"
13
+ ],
14
+ "model_max_length": 8192,
15
+ "pad_token": "<pad>",
16
+ "sp_model_kwargs": {},
17
+ "spaces_between_special_tokens": false,
18
+ "tokenizer_class": "TokenizersBackend",
19
+ "unk_token": "<unk>",
20
+ "use_default_system_prompt": false
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4164dc7f7296b1c51edd8abe3c3ef3a1b2c72a72e649ffa5e0529c159aeffa92
3
+ size 5201