Hugging Face's logo

jonathanli
/
vary-tiny

Text Generation
Transformers
Safetensors
vary_tiny
conversational
Model card Files
xet
Community
jonathanli commited on
Commit
b49436f
·
verified ·
1 Parent(s): da5ece4

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +5 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +53 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +60 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<image>": 50267,
3
+ "<|Assistant|>": 50265,
4
+ "<|User|>": 50266
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|Assistant|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|User|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<image>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50265": {
22
+ "content": "<|Assistant|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50266": {
30
+ "content": "<|User|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50267": {
38
+ "content": "<image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|Assistant|>",
48
+ "<|User|>",
49
+ "<image>"
50
+ ],
51
+ "bos_token": "</s>",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "</s>",
54
+ "errors": "replace",
55
+ "extra_special_tokens": {},
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "<pad>",
58
+ "tokenizer_class": "GPT2Tokenizer",
59
+ "unk_token": "</s>"
60
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff