Files
wehub-resource-sync 1b8708893a
Security Scan / tests (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:12:26 +08:00

57 lines
2.0 KiB
YAML

config_file: |
backend: llama-cpp
context_size: 4096
f16: true
known_usecases:
- chat
mmap: true
stopwords:
- <|im_end|>
- <dummy32000>
- </s>
- <|endoftext|>
function:
# LFM2 Pythonic tool-call syntax: <|tool_call_start|>[name(k="v", ...)]<|tool_call_end|>
# Mirrors common_chat_params_init_lfm2 in llama.cpp/common/chat.cpp.
response_regex:
- '<\|tool_call_start\|>\[(?P<name>\w+)\((?P<arguments>.*?)\)\]<\|tool_call_end\|>'
argument_regex:
- '(?P<key>\w+)\s*=\s*"(?P<value>[^"]*)"'
- '(?P<key>\w+)\s*=\s*(?P<value>-?\d+(?:\.\d+)?|true|false|null)'
argument_regex_key_name: key
argument_regex_value_name: value
template:
chat: |
{{.Input -}}
<|im_start|>assistant
chat_message: |
<|im_start|>{{ .RoleName }}
{{ if .FunctionCall -}}
<|tool_call_start|>
{{ else if eq .RoleName "tool" -}}
<|tool_response_start|>
{{ end -}}
{{ if .Content -}}
{{.Content }}
{{ end -}}
{{ if eq .RoleName "tool" -}}
<|tool_response_end|>
{{ end -}}
{{ if .FunctionCall -}}
{{toJson .FunctionCall}}
{{ end -}}<|im_end|>
completion: |
{{.Input}}
function: |
<|im_start|>system
You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.
List of tools: <|tool_list_start|>[
{{range .Functions}}
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
{{end}}
]<|tool_list_end|>
<|im_end|>
{{.Input -}}
<|im_start|>assistant
name: lfm