Chakita commited on
Commit
9611727
1 Parent(s): a3a8923

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|BOS|>": 50257, "<|PAD|>": 50260, "<|UNK|>": 50259, "<|SEP|>": 50261, "<|EOS|>": 50258}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|BOS|>", "eos_token": "<|EOS|>", "unk_token": "<|UNK|>", "sep_token": "<|SEP|>", "pad_token": "<|PAD|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff