km-tokenizer-khmer / tokenizer_config.json
khopilot's picture
Upload tokenizer_config.json with huggingface_hub
cab1437 verified
{
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"model_max_length": 512,
"pad_token": "<pad>",
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}