| { |
| "add_bos_token": true, |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "1": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50260": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50265": { |
| "content": "<|system|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50266": { |
| "content": "<|user|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50267": { |
| "content": "<|assistant|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50268": { |
| "content": "<|end|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "bos_token": "</s>", |
| "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}", |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<|endoftext|>", |
| "errors": "replace", |
| "extra_special_tokens": {}, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "<pad>", |
| "padding_side": "left", |
| "tokenizer_class": "GPT2Tokenizer", |
| "unk_token": "<unk>" |
| } |
|
|
