| { |
| "add_bos_token": true, |
| "add_eos_token": false, |
| "add_prefix_space": null, |
| "added_tokens_decoder": { |
| "100000": { |
| "content": "<｜begin▁of▁sentence｜>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "100001": { |
| "content": "<｜end▁of▁sentence｜>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "100002": { |
| "content": "ø", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100003": { |
| "content": "ö", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100004": { |
| "content": "ú", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100005": { |
| "content": "ÿ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100006": { |
| "content": "õ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100007": { |
| "content": "÷", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100008": { |
| "content": "û", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100009": { |
| "content": "ý", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100010": { |
| "content": "À", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100011": { |
| "content": "ù", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100012": { |
| "content": "Á", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100013": { |
| "content": "þ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "100014": { |
| "content": "ü", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "bos_token": "<｜begin▁of▁sentence｜>", |
| "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}", |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<｜end▁of▁sentence｜>", |
| "extra_special_tokens": {}, |
| "legacy": true, |
| "max_length": 512, |
| "model_max_length": 4096, |
| "pad_to_multiple_of": null, |
| "pad_token": "<｜end▁of▁sentence｜>", |
| "pad_token_type_id": 0, |
| "padding_side": "left", |
| "sp_model_kwargs": {}, |
| "stride": 0, |
| "tokenizer_class": "LlamaTokenizerFast", |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": null, |
| "use_default_system_prompt": false |
| } |
|
|
