code-search-net-tokenizer / tokenizer.json
mbateman's picture
add tokenizer
2f0fabc
{"version":"1.0","truncation":null,"padding":null,"added_tokens":[{"id":0,"special":true,"content":"<|endoftext|>","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":null,"pre_tokenizer":{"type":"ByteLevel","add_prefix_space":false,"trim_offsets":true},"post_processor":{"type":"ByteLevel","add_prefix_space":true,"trim_offsets":false},"decoder":{"type":"ByteLevel","add_prefix_space":true,"trim_offsets":true},"model":{"type":"BPE","dropout":null,"unk_token":null,"continuing_subword_prefix":"","end_of_word_suffix":"","fuse_unk":false,"vocab":{"<|endoftext|>":0},"merges":[]}}