LowOnMind-5M / tokenizer_config.json
DedeProGames's picture
LowOnMind-5M — 4,920,384 params, 200M tokens fineweb-edu, val ppl 13.23
f9346af verified
Raw
History Blame Contribute Delete
265 Bytes
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"is_local": false,
"local_files_only": false,
"model_max_length": 512,
"pad_token": "<|pad|>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<|unk|>"
}