Hugging Face's logo

tyzhu
/
tiny_LLaMA_1b_8k_intramask_cc_8k_iter-480000-ckpt-step-60000_hf

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Model card Files Community
1
tyzhu commited on
Commit
850ea12
·
verified ·
1 Parent(s): c635b17

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +21 -3
  2. tokenizer_config.json +25 -34
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "</s>",
5
- "unk_token": "<unk>"
 
 
 
 
 
 
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
  }
tokenizer_config.json CHANGED
@@ -1,45 +1,36 @@
1
  {
2
- "add_bos_token": false,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": true,
35
  "model_max_length": 1000000000000000019884624838656,
36
- "pad_token": "</s>",
37
  "padding_side": "left",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
- "tokenizer_file": null,
42
  "truncation_side": "left",
43
- "unk_token": "<unk>",
44
- "use_default_system_prompt": true
 
 
 
 
 
 
45
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": true,
22
  "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
  "padding_side": "left",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
 
27
  "truncation_side": "left",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
  }