codegpt-java-10.2 / tokenizer_config.json
thmk's picture
End of training
5297142
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"name_or_path": "thmk/java-tokenizer-xl",
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}