Hugging Face's logo

kurtpayne
/
skillscan-deberta-adapter

Text Classification
PEFT
ONNX
Safetensors
Transformers
deberta-v2
lora
text-embeddings-inference
Model card Files
xet
 Community
kurtpayne commited on
Commit
7e66fe3
·
verified ·
1 Parent(s): 2c074b6

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +26 -36
  2. model.safetensors +3 -0
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,24 +1,11 @@
1
  {
2
  "architectures": [
3
- "ModernBertForSequenceClassification"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 50281,
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": 50282,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000.0,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
  "hidden_size": 768,
23
  "id2label": {
24
  "0": "LABEL_0",
@@ -30,9 +17,8 @@
30
  "6": "LABEL_6",
31
  "7": "LABEL_7"
32
  },
33
- "initializer_cutoff_factor": 2.0,
34
  "initializer_range": 0.02,
35
- "intermediate_size": 1152,
36
  "label2id": {
37
  "LABEL_0": 0,
38
  "LABEL_1": 1,
@@ -43,24 +29,28 @@
43
  "LABEL_6": 6,
44
  "LABEL_7": 7
45
  },
46
- "layer_norm_eps": 1e-05,
47
- "local_attention": 128,
48
- "local_rope_theta": 10000.0,
49
- "max_position_embeddings": 8192,
50
- "mlp_bias": false,
51
- "mlp_dropout": 0.0,
52
- "model_type": "modernbert",
53
- "norm_bias": false,
54
- "norm_eps": 1e-05,
55
  "num_attention_heads": 12,
56
- "num_hidden_layers": 22,
57
- "pad_token_id": 50283,
58
- "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
59
  "problem_type": "multi_label_classification",
60
- "repad_logits_with_grad": false,
61
- "sep_token_id": 50282,
62
- "sparse_pred_ignore_index": -100,
63
- "sparse_prediction": false,
64
  "transformers_version": "4.57.6",
65
- "vocab_size": 50368
 
66
  }
 
1
  {
2
  "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
  ],
5
+ "attention_probs_dropout_prob": 0.1,
 
 
 
 
 
 
 
 
 
6
  "dtype": "float32",
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
 
 
 
 
9
  "hidden_size": 768,
10
  "id2label": {
11
  "0": "LABEL_0",
 
17
  "6": "LABEL_6",
18
  "7": "LABEL_7"
19
  },
 
20
  "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
  "label2id": {
23
  "LABEL_0": 0,
24
  "LABEL_1": 1,
 
29
  "LABEL_6": 6,
30
  "LABEL_7": 7
31
  },
32
+ "layer_norm_eps": 1e-07,
33
+ "legacy": true,
34
+ "max_position_embeddings": 512,
35
+ "max_relative_positions": -1,
36
+ "model_type": "deberta-v2",
37
+ "norm_rel_ebd": "layer_norm",
 
 
 
38
  "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "pooler_dropout": 0,
42
+ "pooler_hidden_act": "gelu",
43
+ "pooler_hidden_size": 768,
44
+ "pos_att_type": [
45
+ "p2c",
46
+ "c2p"
47
+ ],
48
+ "position_biased_input": false,
49
+ "position_buckets": 256,
50
  "problem_type": "multi_label_classification",
51
+ "relative_attention": true,
52
+ "share_att_key": true,
 
 
53
  "transformers_version": "4.57.6",
54
+ "type_vocab_size": 0,
55
+ "vocab_size": 128100
56
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:783e5e16e9e9c72376d564186ffcc553bbb9772472bb22967c7e1273355ad734
3
+ size 737737736
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:578f7c82780078d69ff72ad1d8669ded45f942feb2c4950b8a8ed5f686992b8f
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6998112520dce45b227e3d2926678830f08fcc68c951bcbbc24fd0bb5987f3f0
3
  size 5905