aegrif commited on
Commit
fb661c3
1 Parent(s): 22c65f4

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|bot|>": 50259,
3
+ "<|context|>": 50258,
4
+ "<|user|>": 50257
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|user|>",
4
+ "<|context|>",
5
+ "<|bot|>"
6
+ ],
7
+ "bos_token": "<|endoftext|>",
8
+ "eos_token": "<|endoftext|>",
9
+ "pad_token": "<|endoftext|>",
10
+ "unk_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
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "special_tokens_map_file": null,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff