Harry Xie commited on
Commit
db8f1bd
1 Parent(s): 5712946

add tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +1 -0
  3. tokenizer_config.json +1 -0
  4. vocab.json +0 -0
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": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
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"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff