tokenizer_config.json
| 1 | { |
| 2 | "add_bos_token": false, |
| 3 | "add_eos_token": false, |
| 4 | "add_prefix_space": true, |
| 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": "<|startoftext|>", |
| 16 | "lstrip": false, |
| 17 | "normalized": false, |
| 18 | "rstrip": false, |
| 19 | "single_word": false, |
| 20 | "special": true |
| 21 | }, |
| 22 | "2": { |
| 23 | "content": "<|endoftext|>", |
| 24 | "lstrip": false, |
| 25 | "normalized": false, |
| 26 | "rstrip": false, |
| 27 | "single_word": false, |
| 28 | "special": true |
| 29 | }, |
| 30 | "6": { |
| 31 | "content": "<|im_start|>", |
| 32 | "lstrip": false, |
| 33 | "normalized": false, |
| 34 | "rstrip": false, |
| 35 | "single_word": false, |
| 36 | "special": false |
| 37 | }, |
| 38 | "7": { |
| 39 | "content": "<|im_end|>", |
| 40 | "lstrip": false, |
| 41 | "normalized": false, |
| 42 | "rstrip": false, |
| 43 | "single_word": false, |
| 44 | "special": true |
| 45 | } |
| 46 | }, |
| 47 | "bos_token": "<|startoftext|>", |
| 48 | "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", |
| 49 | "clean_up_tokenization_spaces": false, |
| 50 | "eos_token": "<|im_end|>", |
| 51 | "legacy": true, |
| 52 | "model_max_length": 4096, |
| 53 | "pad_token": "<unk>", |
| 54 | "sp_model_kwargs": {}, |
| 55 | "spaces_between_special_tokens": false, |
| 56 | "tokenizer_class": "LlamaTokenizer", |
| 57 | "unk_token": "<unk>", |
| 58 | "use_default_system_prompt": false, |
| 59 | "use_fast": true |
| 60 | } |
| 61 | |