Hugging Face's logo

Vikhrmodels
/
Vikhr-7b-0.1

Text Generation
Transformers
PyTorch
Safetensors
Russian
English
mistral
Inference Endpoints
text-generation-inference
Model card Files Community
3
AlexWortega commited on
Commit
dfedd43
•
1 Parent(s): 7b6e848

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +5 -0
  2. special_tokens_map.json +8 -21
  3. tokenizer.json +3 -3
  4. tokenizer_config.json +8 -5
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
special_tokens_map.json CHANGED
@@ -1,23 +1,10 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
32
  }
33
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
  }
33
  ],
tokenizer_config.json CHANGED
@@ -1,11 +1,9 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
@@ -13,7 +11,7 @@
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
- "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
@@ -21,12 +19,17 @@
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
- "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  }
29
  },
 
 
 
 
 
30
  "bos_token": "<s>",
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
  "bos_token": "<s>",
34
  "clean_up_tokenization_spaces": false,
35
  "eos_token": "</s>",