custom_model / tokenizer_config.json
nateg10's picture
Training in progress, step 200
5040a0a verified
raw
history blame
895 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "!",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 16,
"pad_token": "!",
"processor_class": "OwlViTProcessor",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}