spital commited on
Commit
34f878d
1 Parent(s): cf61c33

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -0
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<|endoftext|>", "special_tokens_map_file": null, "name_or_path": "/shared/data/ptwiki/ByteLevelBPE_tokenizer_pt", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}