Update tokenizer_config.json
Browse files- tokenizer_config.json +16 -0
tokenizer_config.json
CHANGED
|
@@ -31,6 +31,22 @@
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"legacy": true,
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": null,
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}\n{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "</s>",
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
+
"pad_token": null,
|
| 40 |
+
"padding_side": "left",
|
| 41 |
+
"sp_model_kwargs": {},
|
| 42 |
+
"spaces_between_special_tokens": false,
|
| 43 |
+
"split_special_tokens": false,
|
| 44 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 45 |
+
"unk_token": "<unk>",
|
| 46 |
+
"use_default_system_prompt": true
|
| 47 |
+
}
|
| 48 |
+
|
| 49 |
+
|
| 50 |
"legacy": true,
|
| 51 |
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
"pad_token": null,
|