clip_text_model_for_masked_lm / tokenizer_config.json
Bingsu's picture
Update tokenizer_config.json
60c0f48
raw
history blame
939 Bytes
{
"add_prefix_space": false,
"additional_special_tokens": [
"<|startoftext|>",
"<|mask|>",
"<|endoftext|>"
],
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": "<|mask|>",
"model_max_length": 512,
"name_or_path": "Bingsu/clip_text_model_for_masked_lm",
"pad_token": "<|endoftext|>",
"special_tokens_map_file": "./special_tokens_map.json",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}