tokenizer/tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "added_tokens_decoder": { |
| 4 | "0": { |
| 5 | "content": "!", |
| 6 | "lstrip": false, |
| 7 | "normalized": false, |
| 8 | "rstrip": false, |
| 9 | "single_word": false, |
| 10 | "special": true |
| 11 | }, |
| 12 | "49406": { |
| 13 | "content": "<|startoftext|>", |
| 14 | "lstrip": false, |
| 15 | "normalized": true, |
| 16 | "rstrip": false, |
| 17 | "single_word": false, |
| 18 | "special": true |
| 19 | }, |
| 20 | "49407": { |
| 21 | "content": "<|endoftext|>", |
| 22 | "lstrip": false, |
| 23 | "normalized": true, |
| 24 | "rstrip": false, |
| 25 | "single_word": false, |
| 26 | "special": true |
| 27 | } |
| 28 | }, |
| 29 | "bos_token": "<|startoftext|>", |
| 30 | "clean_up_tokenization_spaces": true, |
| 31 | "do_lower_case": true, |
| 32 | "eos_token": "<|endoftext|>", |
| 33 | "errors": "replace", |
| 34 | "model_max_length": 77, |
| 35 | "pad_token": "!", |
| 36 | "tokenizer_class": "CLIPTokenizer", |
| 37 | "unk_token": "<|endoftext|>" |
| 38 | } |
| 39 | |