tokenizer_config.json
| 1 | { |
| 2 | "add_bos_token": true, |
| 3 | "add_eos_token": false, |
| 4 | "add_prefix_space": null, |
| 5 | "added_tokens_decoder": { |
| 6 | "0": { |
| 7 | "content": "<unk>", |
| 8 | "lstrip": false, |
| 9 | "normalized": false, |
| 10 | "rstrip": false, |
| 11 | "single_word": false, |
| 12 | "special": true |
| 13 | }, |
| 14 | "1": { |
| 15 | "content": "<s>", |
| 16 | "lstrip": false, |
| 17 | "normalized": false, |
| 18 | "rstrip": false, |
| 19 | "single_word": false, |
| 20 | "special": true |
| 21 | }, |
| 22 | "2": { |
| 23 | "content": "</s>", |
| 24 | "lstrip": false, |
| 25 | "normalized": false, |
| 26 | "rstrip": false, |
| 27 | "single_word": false, |
| 28 | "special": true |
| 29 | }, |
| 30 | "32000": { |
| 31 | "content": "<image>", |
| 32 | "lstrip": false, |
| 33 | "normalized": false, |
| 34 | "rstrip": false, |
| 35 | "single_word": false, |
| 36 | "special": true |
| 37 | }, |
| 38 | "32001": { |
| 39 | "content": "<pad>", |
| 40 | "lstrip": false, |
| 41 | "normalized": false, |
| 42 | "rstrip": false, |
| 43 | "single_word": false, |
| 44 | "special": true |
| 45 | } |
| 46 | }, |
| 47 | "bos_token": "<s>", |
| 48 | "clean_up_tokenization_spaces": false, |
| 49 | "eos_token": "</s>", |
| 50 | "extra_special_tokens": { |
| 51 | "image_token": "<image>" |
| 52 | }, |
| 53 | "image_token": "<image>", |
| 54 | "legacy": false, |
| 55 | "model_max_length": 1000000000000000019884624838656, |
| 56 | "pad_token": "<pad>", |
| 57 | "padding_side": "left", |
| 58 | "processor_class": "LlavaProcessor", |
| 59 | "sp_model_kwargs": {}, |
| 60 | "tokenizer_class": "LlamaTokenizer", |
| 61 | "trust_remote_code": false, |
| 62 | "unk_token": "<unk>", |
| 63 | "use_default_system_prompt": false |
| 64 | } |
| 65 | |