aliafshar/
gemma3-it-qat-tools:27b

1,568 3 months ago

Gemma3 instruction-tuned and quantized with tool/functions using a faithful representation of the Google DeepMind recommended tool calling methodology. Runs remarkably well on old GPUs and CPU.

vision tools 1b 4b 12b 27b
... /
template
0827f42cd04e · 1.2kB
{{- if .System }}<start_of_turn>user
{{ .System }}<end_of_turn>
{{- end }}
{{- if .Tools }}<start_of_turn>user
You have access to functions. If you decide to invoke any of the function(s),
For each function call, you MUST put it in the format of:
```tool_code
{"name": function name, "parameters": dictionary of argument name and its value}
```
You SHOULD NOT include any other text in the response if you call a function.
The response to a function call will be wrapped in ```tool_output```
The available functions are: [
{{- range $.Tools }}
{"type": "function", "function": {{ .Function }}}
{{- end }}
]
<end_of_turn>
{{- end }}
{{- 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
{{ if .Content }}{{ .Content }}
{{- else if .ToolCalls }}```tool_code
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments}}}
{{ end }}```
{{- end }}
{{ if not $last }}<end_of_turn>
{{ end }}
{{- end }}
{{- end }}