Update tokenizer_config.json with chat_template
#11
by
mgoin
- opened
- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
@@ -8002,6 +8002,7 @@
|
|
8002 |
}
|
8003 |
},
|
8004 |
"bos_token": "<s>",
|
|
|
8005 |
"clean_up_tokenization_spaces": true,
|
8006 |
"eos_token": "</s>",
|
8007 |
"model_input_names": [
|
|
|
8002 |
}
|
8003 |
},
|
8004 |
"bos_token": "<s>",
|
8005 |
+
"chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message[\"role\"] == \"user\" %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST]\" + system_message + \"\n\n\" }}\n {%- else %}\n {{- \"[INST]\" }}\n {%- endif %}\n {%- if message[\"content\"] is not string %}\n {%- for chunk in message[\"content\"] %}\n {%- if chunk[\"type\"] == \"text\" %}\n {{- chunk[\"content\"] }}\n {%- elif chunk[\"type\"] == \"image\" %}\n {{- \"[IMG]\" }}\n {%- else %}\n {{- raise_exception(\"Unrecognized content type!\") }}\n {%- endif %}\n {%- endfor %}\n {%- else %}\n {{- message[\"content\"] }}\n {%- endif %}\n {{- \"[/INST]\" }}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- message[\"content\"] + eos_token}}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n {%- endif %}\n{%- endfor %}"
|
8006 |
"clean_up_tokenization_spaces": true,
|
8007 |
"eos_token": "</s>",
|
8008 |
"model_input_names": [
|