johnrobinsn commited on
Commit
7c83117
1 Parent(s): 15287fc

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "model_max_length": 2048,
8
+ "special_tokens_map_file": "/home/jr/.cache/huggingface/hub/models--togethercomputer--RedPajama-INCITE-Base-3B-v1/snapshots/6ae8e763f8ea033bd28f83998b57a8623353f8b5/special_tokens_map.json",
9
+ "tokenizer_class": "GPTNeoXTokenizer",
10
+ "unk_token": "<|endoftext|>"
11
+ }