Hugging Face's logo

peft-internal-testing
/
tiny-random-OPTForCausalLM-extended-vocab

PEFT
Safetensors
Model card Files Community
smangrul commited on
Commit
66a878b
•
1 Parent(s): 4afa375

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +6 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +38 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +78 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 50265,
3
+ "<|im_start|>assistant": 50267,
4
+ "<|im_start|>system": 50268,
5
+ "<|im_start|>user": 50266
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>user",
4
+ "<|im_start|>assistant",
5
+ "<|im_start|>system",
6
+ "<|im_end|>",
7
+ "<s>",
8
+ "<pad>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<pad>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50265": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50266": {
38
+ "content": "<|im_start|>user",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50267": {
46
+ "content": "<|im_start|>assistant",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50268": {
54
+ "content": "<|im_start|>system",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<|im_start|>user",
64
+ "<|im_start|>assistant",
65
+ "<|im_start|>system",
66
+ "<|im_end|>",
67
+ "<s>",
68
+ "<pad>"
69
+ ],
70
+ "bos_token": "<s>",
71
+ "clean_up_tokenization_spaces": true,
72
+ "eos_token": "<|im_end|>",
73
+ "errors": "replace",
74
+ "model_max_length": 100,
75
+ "pad_token": "<pad>",
76
+ "tokenizer_class": "GPT2Tokenizer",
77
+ "unk_token": "</s>"
78
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff