ColUltraVBERT / tokenizer_config.json
hmellor's picture
hmellor HF Staff
athrael-soju's picture
Duplicate from athrael-soju/ColUltraVBERT
e730d84
Raw History Blame Contribute Delete
591 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [
"<fake_token_around_image>",
"<image>",
"<end_of_utterance>"
],
"is_local": true,
"local_files_only": true,
"mask_token": "<|mask|>",
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"processor_class": "Idefics3Processor",
"sep_token": "<|sep|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}