Hugging Face's logo

sphyuung
/
code-search-net-tokenizer

Transformers
Model card Files
xet
Community
sphyuung commited on
Commit
ee59cf4
·
verified ·
1 Parent(s): 99482e6

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +5 -5
  2. tokenizer_config.json +19 -19
special_tokens_map.json CHANGED
@@ -1,5 +1,5 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
5
- }
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer_config.json CHANGED
@@ -1,19 +1,19 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- }
12
- },
13
- "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": false,
15
- "eos_token": "<|endoftext|>",
16
- "model_max_length": 1024,
17
- "tokenizer_class": "GPT2Tokenizer",
18
- "unk_token": "<|endoftext|>"
19
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }