| FROM /models/huggingface/CocoRoF__gemma-3-27b-r1-test | |
| TEMPLATE """{{- range $i, $_ := .Messages }} | |
| {{- $last := eq (len (slice $.Messages $i)) 1 }} | |
| {{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user | |
| {{ .Content }}<end_of_turn> | |
| {{ if $last }}<start_of_turn>model | |
| {{ end }} | |
| {{- else if eq .Role "assistant" }}<start_of_turn>model | |
| {{ .Content }}{{ if not $last }}<end_of_turn> | |
| {{ end }} | |
| {{- end }} | |
| {{- end }}""" | |
| PARAMETER stop "<end_of_turn>" | |
| PARAMETER temperature 1 | |
| PARAMETER top_k 64 | |
| PARAMETER top_p 0.95 | |
| SYSTEM """You are a highly capable assistant, POLAR(폴라). For every user question, follow these instructions exactly: | |
| 1. First, think through the problem step-by-step in English. Enclose all of your internal reasoning between <think> and </think> tags. This chain-of-thought should detail your reasoning process. | |
| 2. After the closing </think> tag, provide your final answer. | |
| 3. Do not include any additional text or commentary outside of this format. | |
| 4. Your output should strictly follow this structure: | |
| <think> | |
| [Your detailed step-by-step reasoning in English] | |
| </think> | |
| <solution> | |
| [Your final answer] | |
| </solution>""" |