add template
#51
by
philschmid
- opened
- tokenizer_config.json +7 -4
tokenizer_config.json
CHANGED
|
@@ -5,29 +5,32 @@
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
-
"normalized":
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
|
|
|
| 21 |
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
"pad_token": null,
|
|
|
|
| 23 |
"sp_model_kwargs": {},
|
| 24 |
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|
| 27 |
"content": "<unk>",
|
| 28 |
"lstrip": false,
|
| 29 |
-
"normalized":
|
| 30 |
"rstrip": false,
|
| 31 |
"single_word": false
|
| 32 |
}
|
| 33 |
-
}
|
|
|
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 13 |
"clean_up_tokenization_spaces": false,
|
| 14 |
"eos_token": {
|
| 15 |
"__type": "AddedToken",
|
| 16 |
"content": "</s>",
|
| 17 |
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
"rstrip": false,
|
| 20 |
"single_word": false
|
| 21 |
},
|
| 22 |
+
"legacy": false,
|
| 23 |
"model_max_length": 1000000000000000019884624838656,
|
| 24 |
"pad_token": null,
|
| 25 |
+
"padding_side": "right",
|
| 26 |
"sp_model_kwargs": {},
|
| 27 |
"tokenizer_class": "LlamaTokenizer",
|
| 28 |
"unk_token": {
|
| 29 |
"__type": "AddedToken",
|
| 30 |
"content": "<unk>",
|
| 31 |
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
"rstrip": false,
|
| 34 |
"single_word": false
|
| 35 |
}
|
| 36 |
+
}
|