Hugging Face's logo

BobaZooba
/
AntModel-7B-XLLM-Demo

Text Generation
Transformers
Safetensors
mistral
Inference Endpoints
text-generation-inference
8-bit precision
bitsandbytes
Model card Files Community
BobaZooba commited on
Commit
04e1cca
•
1 Parent(s): 3c66d42

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +8 -3
  2. tokenizer.json +3 -3
  3. tokenizer_config.json +9 -4
special_tokens_map.json CHANGED
@@ -1,15 +1,20 @@
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
  },
@@ -17,7 +22,7 @@
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
  "bos_token": {
8
  "content": "<s>",
9
  "lstrip": false,
10
+ "normalized": false,
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
  "eos_token": {
15
  "content": "</s>",
16
  "lstrip": false,
17
+ "normalized": false,
18
  "rstrip": false,
19
  "single_word": false
20
  },
 
22
  "unk_token": {
23
  "content": "<unk>",
24
  "lstrip": false,
25
+ "normalized": false,
26
  "rstrip": false,
27
  "single_word": false
28
  }
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
@@ -3,7 +3,7 @@
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
- "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
@@ -11,7 +11,7 @@
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
- "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,19 +19,24 @@
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>",
32
  "legacy": true,
33
  "model_max_length": 1000000000000000019884624838656,
34
  "pad_token": "</s>",
 
35
  "sp_model_kwargs": {},
36
  "spaces_between_special_tokens": false,
37
  "tokenizer_class": "LlamaTokenizer",
 
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>",
36
  "legacy": true,
37
  "model_max_length": 1000000000000000019884624838656,
38
  "pad_token": "</s>",
39
+ "padding_side": "left",
40
  "sp_model_kwargs": {},
41
  "spaces_between_special_tokens": false,
42
  "tokenizer_class": "LlamaTokenizer",