novamind-256m / tokenizer /tokenizer_config.json
achbj
feat: implement project scaffolding, training pipelines, and utility scripts for NovaMind model development
3dfccac
Raw
History Blame Contribute Delete
326 Bytes
{
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"is_local": false,
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"sp_model_kwargs": {},
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}