DevilishDaoSaint commited on
Commit
4732d8c
1 Parent(s): 5c612b6

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
special_tokens_map.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "bos_token": {
3
- "content": "<|startoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
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": "<|im_end|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
- size 1033105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "add_bos_token": false,
3
  "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
@@ -12,7 +12,7 @@
12
  "special": true
13
  },
14
  "1": {
15
- "content": "<|startoftext|>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
@@ -20,7 +20,23 @@
20
  "special": true
21
  },
22
  "2": {
23
- "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
@@ -28,15 +44,20 @@
28
  "special": true
29
  }
30
  },
31
- "bos_token": "<|startoftext|>",
 
 
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "<|endoftext|>",
34
  "legacy": true,
35
- "model_max_length": 4096,
36
  "pad_token": "<unk>",
37
  "padding_side": "left",
38
  "sp_model_kwargs": {},
 
39
  "tokenizer_class": "LlamaTokenizer",
 
40
  "unk_token": "<unk>",
41
- "use_default_system_prompt": false
 
42
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
 
12
  "special": true
13
  },
14
  "1": {
15
+ "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
 
20
  "special": true
21
  },
22
  "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
  "lstrip": false,
41
  "normalized": false,
42
  "rstrip": false,
 
44
  "special": true
45
  }
46
  },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
  "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
  "legacy": true,
53
+ "model_max_length": 32768,
54
  "pad_token": "<unk>",
55
  "padding_side": "left",
56
  "sp_model_kwargs": {},
57
+ "spaces_between_special_tokens": false,
58
  "tokenizer_class": "LlamaTokenizer",
59
+ "trust_remote_code": false,
60
  "unk_token": "<unk>",
61
+ "use_default_system_prompt": true,
62
+ "use_fast": true
63
  }