Update tokenizer_2/tokenizer_config.json

This commit is contained in:
Yatharth Gupta 2023-10-21 15:32:20 +00:00 committed by huggingface-web
parent e762ad4cc9
commit 645c9ca46d

@ -1,40 +1,33 @@
{ {
"add_prefix_space": false, "add_prefix_space": false,
"added_tokens_decoder": { "bos_token": {
"0": { "__type": "AddedToken",
"content": "!", "content": "<|startoftext|>",
"lstrip": false, "lstrip": false,
"normalized": false, "normalized": true,
"rstrip": false, "rstrip": false,
"single_word": 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
}
}, },
"additional_special_tokens": [],
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true, "clean_up_tokenization_spaces": true,
"do_lower_case": true, "do_lower_case": true,
"eos_token": "<|endoftext|>", "eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace", "errors": "replace",
"model_max_length": 77, "model_max_length": 77,
"pad_token": "!", "pad_token": "!",
"tokenizer_class": "CLIPTokenizer", "tokenizer_class": "CLIPTokenizer",
"tokenizer_file": null, "unk_token": {
"unk_token": "<|endoftext|>" "__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
} }