tokenizer_config.json 727 B

1234567891011121314151617181920212223242526272829303132333435
  1. {
  2. "add_bos_token": true,
  3. "add_eos_token": false,
  4. "bos_token": {
  5. "__type": "AddedToken",
  6. "content": "<s>",
  7. "lstrip": false,
  8. "normalized": true,
  9. "rstrip": false,
  10. "single_word": false
  11. },
  12. "clean_up_tokenization_spaces": false,
  13. "eos_token": {
  14. "__type": "AddedToken",
  15. "content": "</s>",
  16. "lstrip": false,
  17. "normalized": true,
  18. "rstrip": false,
  19. "single_word": false
  20. },
  21. "model_max_length": 1024,
  22. "pad_token": null,
  23. "padding_side": "right",
  24. "sp_model_kwargs": {},
  25. "tokenizer_class": "LlamaTokenizer",
  26. "unk_token": {
  27. "__type": "AddedToken",
  28. "content": "<unk>",
  29. "lstrip": false,
  30. "normalized": true,
  31. "rstrip": false,
  32. "single_word": false
  33. }
  34. }