an hour ago

The foundational weights of Qwen/Qwen3.5-9B with selected specialization to maximize coding + agentic work at a small size using distillation/donar weights. ~7 GB loaded. Q4_K_M.

tools thinking
87044a4d5a3d ยท 1.6kB
{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}
{{- if .Tools }}<|im_start|>system
# Tools
You have access to the following functions:
<tools>
{{ range .Tools }}
{{ . }}
{{ end }}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<think>
Brief explanation of next step or parameter rationale
</think>
<tool_call>
{"name": "example_function_name", "arguments": {"example_parameter_1": "value_1"}}
</tool_call>
<IMPORTANT>
- All planning, hypothesis testing, and error reflection MUST be placed strictly inside the <think></think> block.
- Output the <tool_call> block IMMEDIATELY after thinking with NO conversational text before it.
- The <tool_call> tag MUST be at the very beginning of a new line, with NO indentation.
- For multiple calls in parallel, output a separate <tool_call></tool_call> block for EACH function.
</IMPORTANT><|im_end|>
{{ end }}
{{- range .Messages }}
{{- if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
{{ else if eq .Role "assistant" }}<|im_start|>assistant
{{- if .Thinking }}<think>
{{ .Thinking }}
</think>
{{ end }}
{{- if .Content }}{{ .Content }}{{ end }}
{{- if .ToolCalls }}
{{ range .ToolCalls }}<tool_call>
{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
</tool_call>
{{ end }}
{{- end }}<|im_end|>
{{ else if eq .Role "tool" }}<|im_start|>user
<tool_response>
{{ .Content }}
</tool_response><|im_end|>
{{ end }}
{{- end }}<|im_start|>assistant
<think>