MateuszW commited on
Commit
4a09c09
1 Parent(s): c3f21b8

Upload DebertaV2ForQuestionAnswering

Browse files
Files changed (2) hide show
  1. config.json +41 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mateusz15wozny/master_thesis/models/not-multi-deberta/checkpoint-1293",
3
+ "architectures": [
4
+ "DebertaV2ForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "language": "english",
13
+ "layer_norm_eps": 1e-07,
14
+ "max_position_embeddings": 512,
15
+ "max_relative_positions": -1,
16
+ "model_type": "deberta-v2",
17
+ "name": "DebertaV2",
18
+ "norm_rel_ebd": "layer_norm",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 0,
22
+ "pooler_dropout": 0,
23
+ "pooler_hidden_act": "gelu",
24
+ "pooler_hidden_size": 1024,
25
+ "pos_att_type": [
26
+ "p2c",
27
+ "c2p"
28
+ ],
29
+ "position_biased_input": false,
30
+ "position_buckets": 256,
31
+ "relative_attention": true,
32
+ "share_att_key": true,
33
+ "summary_activation": "tanh",
34
+ "summary_last_dropout": 0,
35
+ "summary_type": "first",
36
+ "summary_use_proj": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.29.0.dev0",
39
+ "type_vocab_size": 0,
40
+ "vocab_size": 128100
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c20aa1457c1f2180993fc2eca649036c42e047c6ca04d317708af79fd6994aa
3
+ size 1736191729