dvruette commited on
Commit
b10a098
1 Parent(s): 4422c09

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|prompter|>",
5
+ "<|prefix_end|>",
6
+ "<|assistant|>",
7
+ "<|prefix_begin|>"
8
+ ],
9
+ "bos_token": "<|endoftext|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "pad_token": "<|padding|>",
12
+ "sep_token": "<|endoftext|>",
13
+ "unk_token": "<|endoftext|>"
14
+ }
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": 1000000000000000019884624838656,
6
+ "special_tokens_map_file": "/home/ubuntu/Open-Assistant/model/model_training/.cache/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }