EdBerg commited on
Commit
b2fe4b4
1 Parent(s): 819fcf5

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
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
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
+ "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,11 +1,10 @@
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 +12,7 @@
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
- "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
@@ -21,7 +20,15 @@
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
- "normalized": true,
 
 
 
 
 
 
 
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
@@ -32,8 +39,7 @@
32
  "eos_token": "</s>",
33
  "model_max_length": 1000000000000000019884624838656,
34
  "pad_token": "</s>",
35
- "sp_model_kwargs": {},
36
- "tokenizer_class": "LlamaTokenizer",
37
- "unk_token": "<unk>",
38
- "use_default_system_prompt": false
39
  }
 
1
  {
2
+ "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<unk>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<s>",
14
  "lstrip": false,
15
+ "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "</s>",
42
+ "padding_side": "left",
43
+ "tokenizer_class": "BloomTokenizer",
44
+ "unk_token": "<unk>"
 
45
  }