@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 253a98078a
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, 04:15 UTC

Add chat templates for ChatGLM (#3418)

Dinghow Yang committed Mar 15, 2024 at 14:19 UTC 253a98078a21a014c263bea9f99ae9234a263670
2 files changed +36
examples/template_chatglm.jinja new
+18
@@ -0,0 +1,18 @@
1 +{%- set counter = namespace(index=0) -%}
2 +{%- for message in messages -%}
3 + {%- if message['role'] == 'user' -%}
4 + {{- '[Round ' + counter.index|string + ']\n问:' + message['content'] -}}
5 + {%- set counter.index = counter.index + 1 -%}
6 + {%- endif -%}
7 + {%- if message['role'] == 'assistant' -%}
8 + {{- '\n答:' + message['content'] -}}
9 + {%- if (loop.last and add_generation_prompt) or not loop.last -%}
10 + {{- '\n' -}}
11 + {%- endif -%}
12 + {%- endif -%}
13 +{%- endfor -%}
14 +
15 +
16 +{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
17 + {{- '\n答:' -}}
18 +{%- endif -%}
\ No newline at end of file
examples/template_chatglm2.jinja new
+18
@@ -0,0 +1,18 @@
1 +{%- set counter = namespace(index=1) -%}
2 +{%- for message in messages -%}
3 + {%- if message['role'] == 'user' -%}
4 + {{- '[Round ' + counter.index|string + ']\n\n问:' + message['content'] -}}
5 + {%- set counter.index = counter.index + 1 -%}
6 + {%- endif -%}
7 + {%- if message['role'] == 'assistant' -%}
8 + {{- '\n\n答:' + message['content'] -}}
9 + {%- if (loop.last and add_generation_prompt) or not loop.last -%}
10 + {{- '\n\n' -}}
11 + {%- endif -%}
12 + {%- endif -%}
13 +{%- endfor -%}
14 +
15 +
16 +{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
17 + {{- '\n\n答:' -}}
18 +{%- endif -%}
\ No newline at end of file