Add alpaca chat template to the Tokenizer (#6)
Browse files- Add alpaca chat template to the Tokenizer (c15d70465e2fc46c3c4d7fec8fb62f533d4ef09b)
Co-authored-by: Shaun Prince <[email protected]>
- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
@@ -27,6 +27,7 @@
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
|
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
+
"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 %}",
|
31 |
"additional_special_tokens": [],
|
32 |
"bos_token": "<s>",
|
33 |
"clean_up_tokenization_spaces": false,
|