metaclip-b32-400m / tokenizer_config.json
GeorgeBredis's picture
Upload processor
d09846e
raw
history blame
968 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"processor_class": "CLIPProcessor",
"tokenizer_class": "CLIPTokenizer",
"tokenizer_file": "/Users/georgebredis/.cache/huggingface/hub/models--laion--CLIP-ViT-B-32-256x256-DataComp-s34B-b86K/snapshots/0e9ac9033bafd4d8d13aa9ce8624a2c7fdc8edca/tokenizer.json",
"unk_token": "<|endoftext|>"
}