@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 74cd5abdd1
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 05:30 UTC

Add baichuan chat template jinjia file (#2390)

KKY committed Jan 9, 2024 at 11:13 UTC 74cd5abdd14b8a7b24a6bf4929f64ae59a3bbd5c
1 file changed +22
examples/template_baichuan.jinja new
+22
@@ -0,0 +1,22 @@
1 +{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}
2 +
3 +{% for message in messages %}
4 +{% if message['role'] == 'user' %}
5 +<reserved_106>
6 +{{ message['content']|trim -}}
7 +{% if not loop.last %}
8 +
9 +
10 +{% endif %}
11 +{% elif message['role'] == 'assistant' %}
12 +<reserved_107>
13 +{{ message['content']|trim -}}
14 +{% if not loop.last %}
15 +
16 +
17 +{% endif %}
18 +{% endif %}
19 +{% endfor %}
20 +{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}
21 +<reserved_107>
22 +{% endif %}
\ No newline at end of file