SindhiLM / tokenizer_config.json
aakashMeghwar01's picture
Upload tokenizer
59c2a98 verified
{
"backend": "tokenizers",
"is_local": true,
"max_length": 512,
"model_max_length": 512,
"pad_to_multiple_of": null,
"pad_token": "<|pad|>",
"pad_token_type_id": 0,
"padding_side": "right",
"special_tokens": {
"eos": "<|endoftext|>",
"pad": "<|pad|>",
"unk": "<|unk|>"
},
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"vocab_size": 24000
}