samai-4b / tokenizer_config.json
tchbcb's picture
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
ac0d936 verified
Raw History Blame Contribute Delete
389 Bytes
{
"backend": "tokenizers",
"bos_token": "<|start▁of▁sentence|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|end▁of▁sentence|>",
"is_local": true,
"legacy": true,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|▁pad▁|>",
"sp_model_kwargs": {},
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}