| { |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "64000": { |
| "content": "<|pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "64001": { |
| "content": "<|im_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "64002": { |
| "content": "<|im_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "additional_special_tokens": [ |
| "<|im_start|>", |
| "<|im_end|>" |
| ], |
| "bos_token": "<|im_start|>", |
| "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<|im_end|>", |
| "extra_special_tokens": {}, |
| "max_length": 256, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_to_multiple_of": null, |
| "pad_token": "<|im_end|>", |
| "pad_token_type_id": 0, |
| "padding_side": "right", |
| "stride": 0, |
| "tokenizer_class": "GPT2Tokenizer", |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": "<|endoftext|>" |
| } |
|
|
