tokenizer_config.json
| 1 | { |
| 2 | "added_tokens_decoder": { |
| 3 | "1": { |
| 4 | "content": "</s>", |
| 5 | "lstrip": true, |
| 6 | "normalized": false, |
| 7 | "rstrip": true, |
| 8 | "single_word": false, |
| 9 | "special": true |
| 10 | }, |
| 11 | "2": { |
| 12 | "content": "<unk>", |
| 13 | "lstrip": true, |
| 14 | "normalized": false, |
| 15 | "rstrip": true, |
| 16 | "single_word": false, |
| 17 | "special": true |
| 18 | } |
| 19 | }, |
| 20 | "additional_special_tokens": [], |
| 21 | "clean_up_tokenization_spaces": true, |
| 22 | "do_lower_case": true, |
| 23 | "eos_token": "</s>", |
| 24 | "model_input_names": [ |
| 25 | "input_ids" |
| 26 | ], |
| 27 | "model_max_length": 64, |
| 28 | "pad_token": "</s>", |
| 29 | "processor_class": "SiglipProcessor", |
| 30 | "sp_model_kwargs": {}, |
| 31 | "tokenizer_class": "SiglipTokenizer", |
| 32 | "unk_token": "<unk>" |
| 33 | } |
| 34 | |