Hugging Face's logo

WesleySantos
/
user_level_filter

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Model card Files
xet
Community
7

Upload tokenizer

#4
by WesleySantos - opened
base: refs/heads/main
←
from: refs/pr/4
Discussion Files changed
+52
-46
Files changed (5) hide show
  1. added_tokens.json +6 -0
  2. special_tokens_map.json +3 -21
  3. tokenizer.json +1 -1
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +39 -24
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 32000,
4
+ "<s>": 1,
5
+ "<unk>": 0
6
+ }
special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "</s>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  },
15
  {
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,32 +1,47 @@
1
  {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
10
  "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- }
32
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
  },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
  "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
 
 
 
 
 
 
 
40
  "legacy": false,
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "</s>",
43
  "sp_model_kwargs": {},
44
  "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
 
 
 
 
 
 
47
  }