tokenizer_config.json 787 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. "legacy": true,
  22. "use_default_system_prompt": false,
  23. "model_max_length": 1000000000000000019884624838656,
  24. "pad_token": null,
  25. "sp_model_kwargs": {},
  26. "tokenizer_class": "LlamaTokenizerFast",
  27. "unk_token": {
  28. "__type": "AddedToken",
  29. "content": "<unk>",
  30. "lstrip": false,
  31. "normalized": true,
  32. "rstrip": false,
  33. "single_word": false
  34. }
  35. }