tiny-audio-multitask / tokenizer_config.json
mazesmazes's picture
Training in progress - step 1000
bd16460 verified
{
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"extra_special_tokens": [
"<audio>"
],
"fast": false,
"is_local": false,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 131072,
"model_specific_special_tokens": {},
"pad_token": "<|finetune_right_pad_id|>",
"tokenizer_class": "TokenizersBackend"
}