cho3ov commited on
Commit
e979124
·
1 Parent(s): ee2adca

Upload 7 files

Browse files
midm_bitext_tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98789fa1bf89a1f9692889fb4a0029d3d096a9109cebf4f6bce1a255f2701378
3
+ size 1457356
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": "</s>",
10
+ "pad_token": "<pad>",
11
+ "unk_token": "<unk>"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "auto_map": {
38
+ "AutoTokenizer": [
39
+ "KT-AI/midm-bitext-S-7B-inst-v1--midm_bitext_tokenization.Midm_bitext_Tokenizer",
40
+ null
41
+ ]
42
+ },
43
+ "bos_token": "<s>",
44
+ "clean_up_tokenization_spaces": true,
45
+ "eos_token": "</s>",
46
+ "extra_ids": 0,
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "<pad>",
49
+ "sp_model_kwargs": {},
50
+ "tokenizer_class": "Midm_bitext_Tokenizer",
51
+ "unk_token": "<unk>"
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce82d2ce819e166c4111c7ebeaa313efe2ec50df4af97c6d7a455592981cb8bb
3
+ size 4664