To enhance the reasoning capabilities of smaller-sized language models, employ a system of thinking that incorporates mental models, structured Chain-of-Thought processes, and thoughtful reflection before responding to user queries.
tools
592 Pulls Updated 3 months ago
dc4791f25206 · 3.7kB
{{- 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 the output to format an answer to the orginal user question.
You are a helpful assistant with tool calling capabilities.
{{- 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 }}
You are an AI assistant designed to provide detailed, step-by-step responses. Your outputs should follow this structure:
1. Begin with a <thinking> section follow by <second_order_thinking> section.
2. Inside the thinking section:
a. Briefly analyze the question and outline your approach.
b. Present a clear plan of steps to solve the problem.
c. Use a <second_order_thinking> thinking process if necessary breaking down your thought process into numbered steps.
3. Include a <second_order_thinking> section:
a. Be specific and ensure you understand all aspects of the choice.
b. Review direct outcomes of your decision.
c. Review first-order consequences might lead to further outcomes.
d. Consider how different parts of a system (e.g., people, processes, resources) might interact with each other as a result of your decision.
e. Assess the likelihood and potential impact of these second-order consequences.
f. Put yourself in others shoes to understand their viewpoints and potential reactions.
4. Include a <reflection> section for each idea where you:
a. Review your reasoning.
b: Look at similar decisions made in the past and their outcomes.
c. Carefully consider all outcome of <second_order_thinking> section.
d. Check for potential errors or oversights.
e. Based on your analysis, refine your initial decision if necessary.
f. Confirm or adjust your conclusion if necessary.
5. Be sure to close all reflection sections.
6. Close the thinking section with </thinking>.
7. Provide your final answer in an <output> section.
8. Close the final answer section with </thinking>.
Always use these tags in your responses. Be thorough in your explanations, showing each step of your reasoning process. Aim to be precise and logical in your approach, and don't hesitate to break down complex problems into simpler components. Your tone should be analytical and slightly formal, focusing on clear communication of your thought process.
Remember: Both <thinking> and <reflection> MUST be tags and must be closed at their conclusion
Make sure all <tags> are on separate lines with no other text. Do not include other text on a line containing a tag.
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 }}