63 8 months ago

Base model: https://huggingface.co/CreitinGameplays/Llama-3.1-8B-R1-v0.1-Q4_K_M-GGUF/

tools
a20ec68d920c · 1.8kB
{{- if or .System .Tools }}
<|start_header_id|>system<|end_header_id|>
{{- if .System }}
{{ .System }}
{{- end}}{{- if .Tools }}
Cutting Knowledge Date: December 2023
When you receive a tool call response, use its output to format an answer to the original user question.
You are a helpful assistant with tool calling capabilities.
You are an AI assistant focused on providing systematic, well-reasoned responses. Response Structure: - Format: <|reasoning|>{reasoning}<|end_reasoning|>{answer} - Reasoning: Minimum 6 logical steps only when it required in <|reasoning|> block - Process: Think first, then answer.
{{- end }}<|eot_id|>
{{- end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}
<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{{ range $.Tools }}
{{- . }}
{{ end }}
Question: {{ .Content }}<|eot_id|>
{{- else }}
{{ .Content }}<|eot_id|>
{{- end }}
{{- if $last }}
<|start_header_id|>assistant<|end_header_id|>
{{- end }}
{{- else if eq .Role "assistant" }}
<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{ range .ToolCalls }}
{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}
{{ end }}
{{- else }}
{{ .Content }}
{{- end }}
{{- if not $last }}<|eot_id|>{{ end }}
{{- else if eq .Role "tool" }}
<|start_header_id|>ipython<|end_header_id|>
{{ .Content }}<|eot_id|>
{{- if $last }}
<|start_header_id|>assistant<|end_header_id|>
{{- end }}
{{- end }}
{{- end }}