MoritzLaurer HF staff commited on
Commit
ff38ba4
1 Parent(s): c2d21f9

Upload DebertaV2ForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +43 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./results/deberta-v3-large-zeroshot-2023-10-02-12-57/best-deberta-v3-large-20231002",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "true",
12
+ "1": "not_true"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "label2id": {
17
+ "not_true": 1,
18
+ "true": 0
19
+ },
20
+ "layer_norm_eps": 1e-07,
21
+ "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 1024,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.33.3",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 128100
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9baeb52052aee3edc942bedf469008ddbf8d51dd4ca008b0e81accea88e10ee
3
+ size 870258677