Hugging Face's logo

jonybepary
/
awazz_ai

Text Generation
Transformers
PyTorch
GGUF
llama
text-generation-inference
Inference Endpoints
Model card Files Community
jonybepary commited on
Commit
fc79f71
•
1 Parent(s): f494001

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +22 -11
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +32 -8
special_tokens_map.json CHANGED
@@ -1,13 +1,24 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<fim-prefix>",
5
- "<fim-middle>",
6
- "<fim-suffix>",
7
- "<fim-pad>"
8
- ],
9
- "bos_token": "<|endoftext|>",
10
- "eos_token": "<|endoftext|>",
11
- "pad_token": "<|endoftext|>",
12
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
1
  {
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
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,10 +1,34 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
4
- "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|endoftext|>",
6
- "errors": "replace",
7
- "model_max_length": 2048,
8
- "tokenizer_class": "GPT2Tokenizer",
9
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  }
 
1
  {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "use_default_system_prompt": true
34
  }