vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update deepseek r1 templates (+ put update commands in ./scripts/get_chat_template.py's comments)

Browse source
This commit is contained in:
ochafik 2025-02-09 20:12:28 +00:00
parent 30dcfaa57a
commit e1bff8f66c
4 changed files with 21 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

2
models/templates/deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja
View file

@ -1 +1 @@
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

57
models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja
View file

@ -1,56 +1 @@
{% if not add_generation_prompt is defined %}
{% set add_generation_prompt = false %}
{% endif %}
{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}
{%- for message in messages %}
{%- if message['role'] == 'system' %}
{% set ns.system_prompt = message['content'] %}
{%- endif %}
{%- endfor %}
{{bos_token}}
{{ns.system_prompt}}
{%- for message in messages %}
{%- if message['role'] == 'user' %}
{%- set ns.is_tool = false -%}
{{'<｜User｜>' + message['content']}}
{%- endif %}
{%- if message['role'] == 'assistant' and message['content'] is none %}
{%- set ns.is_tool = false -%}
{%- for tool in message['tool_calls']%}
{%- if not ns.is_first %}
{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}
{%- set ns.is_first = true -%}
{%- else %}
{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}
{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
{%- endif %}
{%- endfor %}
{%- endif %}
{%- if message['role'] == 'assistant' and message['content'] is not none %}
{%- if ns.is_tool %}
{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}
{%- set ns.is_tool = false -%}
{%- else %}
{% set content = message['content'] %}
{% if '</think>' in content %}
{% set content = content.split('</think>')[-1] %}
{% endif %}
{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}
{%- endif %}
{%- endif %}
{%- if message['role'] == 'tool' %}
{%- set ns.is_tool = true -%}
{%- if ns.is_output_first %}
{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}
{%- set ns.is_output_first = false %}
{%- else %}
{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}
{%- endif %}
{%- endif %}
{%- endfor -%}
{% if ns.is_tool %}
{{'<｜tool▁outputs▁end｜>'}}
{% endif %}
{% if add_generation_prompt and not ns.is_tool %}
{{'<｜Assistant｜>'}}
{% endif %}
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

2
models/templates/llama-cpp-deepseek-r1.jinja
View file

@ -72,5 +72,5 @@ Example function tool call syntax:
{%- endfor -%}
{{- flush_tool_outputs() -}}
{%- if add_generation_prompt and not ns.is_tool_outputs -%}
{{- '<｜Assistant｜>' -}}
{{- '<｜Assistant｜><think>\n' -}}
{%- endif -%}

21
scripts/get_chat_template.py Normal file → Executable file
View file

@ -7,9 +7,24 @@
./scripts/get_chat_template.py model_id [variant]
Examples:
./scripts/get_chat_template.py NousResearch/Meta-Llama-3-8B-Instruct
./scripts/get_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use
./scripts/get_chat_template.py meta-llama/Llama-3.2-3B-Instruct
./scripts/get_chat_template.py CohereForAI/c4ai-command-r-plus tool_use | tee models/templates/CohereForAI-c4ai-command-r-plus-tool_use.jinja
./scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 default | tee models/templates/CohereForAI-c4ai-command-r7b-12-2024-default.jinja
./scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 rag | tee models/templates/CohereForAI-c4ai-command-r7b-12-2024-rag.jinja
./scripts/get_chat_template.py CohereForAI/c4ai-command-r7b-12-2024 tool_use | tee models/templates/CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja
./scripts/get_chat_template.py deepseek-ai/DeepSeek-R1-Distill-Llama-8B | tee models/templates/deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja
./scripts/get_chat_template.py deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | tee models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja
./scripts/get_chat_template.py fireworks-ai/llama-3-firefunction-v2 | tee models/templates/fireworks-ai-llama-3-firefunction-v2.jinja
./scripts/get_chat_template.py google/gemma-2-2b-it | tee models/templates/google-gemma-2-2b-it.jinja
./scripts/get_chat_template.py meetkai/functionary-medium-v3. | tee models/templates/meetkai-functionary-medium-v3.jinja
./scripts/get_chat_template.py meetkai/functionary-medium-v3.2 | tee models/templates/meetkai-functionary-medium-v3.2.jinja
./scripts/get_chat_template.py meta-llama/Llama-3.1-8B-Instruct | tee models/templates/meta-llama-Llama-3.1-8B-Instruct.jinja
./scripts/get_chat_template.py meta-llama/Llama-3.2-3B-Instruct | tee models/templates/meta-llama-Llama-3.2-3B-Instruct.jinja
./scripts/get_chat_template.py meta-llama/Llama-3.3-70B-Instruct | tee models/templates/meta-llama-Llama-3.3-70B-Instruct.jinja
./scripts/get_chat_template.py microsoft/Phi-3.5-mini-instruct | tee models/templates/microsoft-Phi-3.5-mini-instruct.jinja
./scripts/get_chat_template.py mistralai/Mistral-Nemo-Instruct-2407 | tee models/templates/mistralai-Mistral-Nemo-Instruct-2407.jinja
./scripts/get_chat_template.py NousResearch/Hermes-2-Pro-Llama-3-8B tool_use | tee models/templates/NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja
./scripts/get_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use | tee models/templates/NousResearch-Hermes-3-Llama-3.1-8B-tool_use.jinja
./scripts/get_chat_template.py Qwen/Qwen2.5-7B-Instruct | tee models/templates/Qwen-Qwen2.5-7B-Instruct.jinja
'''
import json