sllm / tokenizer /fineweb_edu_tokenizer /tokenizer_config.json
geeteshcodes's picture
Initial commit
7f974df verified
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"unk_token": null
}