second_constantine/
magistral-small:24b

61 2 days ago

Building upon Mistral Small 3.2 (2506), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.(quantized UD-Q5_K_XL)

vision tools thinking 24b
... /
template
bda6c9c165c2 · 844B
{{- range $index, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $index)) 1}}
{{- if eq .Role "system" }}[SYSTEM_PROMPT]{{ .Content }}[/SYSTEM_PROMPT]
{{- else if eq .Role "user" }}
{{- if and (le (len (slice $.Messages $index)) 2) $.Tools }}[AVAILABLE_TOOLS]{{ $.Tools }}[/AVAILABLE_TOOLS]
{{- end }}[INST]{{ .Content }}[/INST]
{{- else if eq .Role "assistant" }}
{{- if and $.IsThinkSet (and $last .Thinking) -}}
<think>
{{ .Thinking }}
</think>
{{ end }}
{{- if .Content }}{{ .Content }}
{{- if not (eq (len (slice $.Messages $index)) 1) }}</s>
{{- end }}
{{- else if .ToolCalls }}
{{- range $i, $_ := .ToolCalls }}[TOOL_CALLS]{{ .Function.Name }}[CALL_ID]{{ $i }}[ARGS]{{ .Function.Arguments }}
{{- end }}</s>
{{- end }}
{{- else if eq .Role "tool" }}[TOOL_RESULTS]{"content": {{ .Content }}}[/TOOL_RESULTS]
{{- end }}
{{- end }}