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