pile-of-law-tokenizer / tokenizer_config.json
sam-mosaic's picture
Upload tokenizer
ce1cc1f
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"model_max_length": 16384,
"name_or_path": "pile-of-law-tokenizer",
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}