apertus-8b-coding / tokenizer_config.json
Colby's picture
Training in progress, step 100
2eedbe0 verified
raw
history blame contribute delete
447 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|assistant_end|>",
"is_local": false,
"local_files_only": false,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "left",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}