SupraCMA-8M / tokenizer_config.json
User01110's picture
Benchmark-selected step 0: Open SLM average 30.66%
a2c9b48 verified
Raw
History Blame Contribute Delete
343 Bytes
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"is_local": false,
"local_files_only": false,
"model_max_length": 1000000000,
"pad_token": "<eos>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"vocab_size": 4096
}