Hugging Face's logo

Pclanglais
/
Larth-Mistral

Text Generation
Transformers
PyTorch
French
mistral
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
 Community
1
Pclanglais commited on
Commit
16599e0
·
1 Parent(s): 82d20bb

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +21 -8
  2. tokenizer.json +9 -4
  3. tokenizer_config.json +4 -8
special_tokens_map.json CHANGED
@@ -1,11 +1,24 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
- "bos_token": "<s>",
8
- "eos_token": "</s>",
 
 
 
 
 
 
 
9
  "pad_token": "</s>",
10
- "unk_token": "<unk>"
 
 
 
 
 
 
11
  }
 
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
  "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -9,7 +14,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -18,7 +23,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": false,
22
  "special": true
23
  },
24
  {
@@ -27,7 +32,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": false,
31
  "special": true
32
  }
33
  ],
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": true,
18
  "special": true
19
  },
20
  {
 
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
+ "normalized": true,
27
  "special": true
28
  },
29
  {
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
+ "normalized": true,
36
  "special": true
37
  }
38
  ],
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
- "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
@@ -11,7 +11,7 @@
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,17 +19,13 @@
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>",
 
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
+ "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
+ "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
 
 
 
 
29
  "bos_token": "<s>",
30
  "clean_up_tokenization_spaces": false,
31
  "eos_token": "</s>",