| { |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "1": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "43965": { |
| "content": "None", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128000": { |
| "content": "<|im_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128001": { |
| "content": "<|im_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128002": { |
| "content": "<|start_of_sequence|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128003": { |
| "content": "<|end_of_sequence|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128004": { |
| "content": "<|finetune_right_pad_id|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "128005": { |
| "content": "<|finetune_left_pad_id|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "additional_special_tokens": [ |
| "<|im_start|>", |
| "<|im_end|>" |
| ], |
| "bos_token": "<|start_of_sequence|>", |
| "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}<|start_of_sequence|>{% for message in messages %}{% if message['role'] == 'user' %}<|im_start|>\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% endif %}{% endfor %}", |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<|end_of_sequence|>", |
| "extra_special_tokens": {}, |
| "model_max_length": 2048, |
| "pad_token": "<|finetune_left_pad_id|>", |
| "padding_side": "left", |
| "tokenizer_class": "PreTrainedTokenizerFast", |
| "truncation_side": "right", |
| "vocab_size": 128000 |
| } |
|
|