Hugging Face's logo

TinyPixel
/
OpenELM-270M

Text Generation
Transformers
Safetensors
openelm
custom_code
Model card Files Community
TinyPixel commited on
Commit
b4e2d2f
•
1 Parent(s): 8721166

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -10
  2. tokenizer.json +3 -3
  3. tokenizer_config.json +6 -4
special_tokens_map.json CHANGED
@@ -2,28 +2,21 @@
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": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
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
  },
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
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
@@ -5,7 +5,7 @@
5
  "0": {
6
  "content": "<unk>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
@@ -13,7 +13,7 @@
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
- "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
@@ -21,7 +21,7 @@
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
- "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
@@ -30,8 +30,10 @@
30
  "bos_token": "<s>",
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
 
33
  "model_max_length": 1000000000000000019884624838656,
34
- "pad_token": "<unk>",
 
35
  "sp_model_kwargs": {},
36
  "tokenizer_class": "LlamaTokenizer",
37
  "unk_token": "<unk>",
 
5
  "0": {
6
  "content": "<unk>",
7
  "lstrip": false,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
+ "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
 
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
+ "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
30
  "bos_token": "<s>",
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
33
+ "legacy": false,
34
  "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "padding_side": "right",
37
  "sp_model_kwargs": {},
38
  "tokenizer_class": "LlamaTokenizer",
39
  "unk_token": "<unk>",