codeparrot-ds-2 / tokenizer_config.json
eltonpan's picture
Training in progress, step 5000
78cf2a7
raw
history blame
295 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"name_or_path": "huggingface-course/code-search-net-tokenizer",
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}