tsukumijima commited on
Commit
97e4e6c
·
verified ·
1 Parent(s): 6b5e901

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +37 -0
  2. model.onnx +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer_config.json +19 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForMaskedLM"
4
+ ],
5
+ "attention_head_size": 64,
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "conv_act": "gelu",
8
+ "conv_kernel_size": 3,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-07,
15
+ "max_position_embeddings": 512,
16
+ "max_relative_positions": -1,
17
+ "model_type": "deberta-v2",
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
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.25.1",
35
+ "type_vocab_size": 0,
36
+ "vocab_size": 22012
37
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c598674a3820b31a145faebdced080b9958af5afe263a185a8148e345e253e
3
+ size 1319653019
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "do_subword_tokenize": true,
5
+ "do_word_tokenize": true,
6
+ "jumanpp_kwargs": null,
7
+ "mask_token": "[MASK]",
8
+ "mecab_kwargs": null,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": null,
14
+ "subword_tokenizer_type": "character",
15
+ "sudachi_kwargs": null,
16
+ "tokenizer_class": "BertJapaneseTokenizer",
17
+ "unk_token": "[UNK]",
18
+ "word_tokenizer_type": "basic"
19
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff