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 15, 19:45 UTC
[Misc] Correct deepseek-vl2 chat template (#14558)
Signed-off-by: Isotr0py <2037008807@qq.com>
Isotr0py committed
Mar 11, 2025 at 12:37 UTC
63d635d17962377df089cdc9d4a2684f0b007208
1 file changed
+3
-3
examples/template_deepseek_vl2.jinja
+3
-3
@@ -12,12 +12,12 @@
12
{%- endif -%}
13
14
{%- if message['role'] == 'user' -%}
15
- {{ '<|User|>: ' + message['content'] + '\n' }}
15
+ {{ '<|User|>: ' + message['content'] + '\n\n' }}
16
{%- elif message['role'] == 'assistant' -%}
17
- {{ '<|Assistant|>: ' + message['content'] + eos_token + '\n' }}
17
+ {{ '<|Assistant|>: ' + message['content'] + eos_token + '\n\n' }}
18
{%- endif -%}
19
{%- endfor -%}
20
21
{%- if add_generation_prompt -%}
22
{{ '<|Assistant|>: ' }}
23
-{% endif %}
23
+{%- endif -%}