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 Falcon (#3420)
Dinghow Yang committed
Mar 15, 2024 at 14:19 UTC
21539e68563ae61d2be311d8b8e656fa039f5a5c
2 files changed
+32
examples/template_falcon.jinja
new
+15
@@ -0,0 +1,15 @@
1
+{%- for message in messages -%}
2
+ {%- if message['role'] == 'user' -%}
3
+ {{- 'User: ' + message['content'] -}}
4
+ {%- elif message['role'] == 'assistant' -%}
5
+ {{- 'Assistant: ' + message['content'] -}}
6
+ {%- endif -%}
7
+ {%- if (loop.last and add_generation_prompt) or not loop.last -%}
8
+ {{- '\n' -}}
9
+ {%- endif -%}
10
+{%- endfor -%}
11
+
12
+
13
+{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
14
+ {{- 'Assistant:' -}}
15
+{% endif %}
\ No newline at end of file
examples/template_falcon_180b.jinja
new
+17
@@ -0,0 +1,17 @@
1
+{%- for message in messages -%}
2
+ {%- if message['role'] == 'system' -%}
3
+ {{- 'System: ' + message['content'] -}}
4
+ {%- elif message['role'] == 'user' -%}
5
+ {{- 'User: ' + message['content'] -}}
6
+ {%- elif message['role'] == 'assistant' -%}
7
+ {{- 'Falcon: ' + message['content'] -}}
8
+ {%- endif -%}
9
+ {%- if (loop.last and add_generation_prompt) or not loop.last -%}
10
+ {{- '\n' -}}
11
+ {%- endif -%}
12
+{%- endfor -%}
13
+
14
+
15
+{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
16
+ {{- 'Falcon:' -}}
17
+{% endif %}
\ No newline at end of file