Hugging Face's logo

atharvanighot
/
tinyllama-cpt

Text Generation
Transformers
PyTorch
Safetensors
llama
unsloth
conversational
text-generation-inference
Model card Files
xet
Community
4
atharvanighot commited on
Commit
b5657e0
·
verified ·
1 Parent(s): a09a003

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -6
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +46 -10
special_tokens_map.json CHANGED
@@ -1,20 +1,23 @@
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": {
17
- "content": "</s>",
 
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": {
4
+ "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
+ "eos_token": "</s>",
11
+ "mask_token": {
12
+ "content": "[MASK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false
17
  },
18
+ "pad_token": "</s>",
19
+ "sep_token": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
@@ -26,19 +23,58 @@
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
30
  },
31
  "bos_token": "<s>",
32
  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
 
34
  "eos_token": "</s>",
35
  "extra_special_tokens": {},
36
- "legacy": false,
37
- "model_max_length": 2048,
38
  "pad_token": "</s>",
39
- "padding_side": "right",
40
- "sp_model_kwargs": {},
41
- "tokenizer_class": "LlamaTokenizer",
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": false
44
  }
 
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
 
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
+ },
27
+ "32000": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "[CLS]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "[SEP]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "[MASK]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
  }
67
  },
68
  "bos_token": "<s>",
69
  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
70
  "clean_up_tokenization_spaces": false,
71
+ "cls_token": "[CLS]",
72
  "eos_token": "</s>",
73
  "extra_special_tokens": {},
74
+ "mask_token": "[MASK]",
75
+ "model_max_length": 1000000000000000019884624838656,
76
  "pad_token": "</s>",
77
+ "sep_token": "[SEP]",
78
+ "tokenizer_class": "PreTrainedTokenizerFast",
79
+ "unk_token": "<unk>"
 
 
80
  }