Jaewoo1 commited on
Commit
21da97d
1 Parent(s): 7e5adb7

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|endoftext|>"
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "name_or_path": "/opt/deepsearfing/experiments/sgpt_finetuning/sgpt_model_wiki_mirae_bc/",
6
+ "pad_token": "<|endoftext|>",
7
+ "special_tokens_map_file": "/root/.cache/torch/sentence_transformers/mncai_SGPT-5.8B-wiki-mirae-epoch5/special_tokens_map.json",
8
+ "tokenizer_class": "PreTrainedTokenizerFast"
9
+ }