onnx/tokenizer_config.json
| 1 | { |
| 2 | "add_prefix_space": false, |
| 3 | "bos_token": "<|endoftext|>", |
| 4 | "clean_up_tokenization_spaces": true, |
| 5 | "eos_token": "<|endoftext|>", |
| 6 | "model_max_length": 1024, |
| 7 | "tokenizer_class": "GPT2Tokenizer", |
| 8 | "unk_token": "<|endoftext|>" |
| 9 | } |
| 10 | |