PhoGPT-4B / tokenizer_config.json
dqnguyen's picture
Upload code
5f4117f
raw
history blame
260 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"tokenizer_class": "BloomTokenizer",
"unk_token": "<unk>"
}