Instruction10K512 / tokenizer_config.json
ArmelR's picture
tokenizer stuff
5ead9d8
raw
history blame contribute delete
433 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"name_or_path": "bigcode/santacoder",
"special_tokens_map_file": "/home/armelzebaze/.cache/huggingface/hub/models--bigcode--santacoder/snapshots/6a4fb77ff71c32c34dc8c61af500c7a7ca17c1a6/special_tokens_map.json",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}