TwinkleAI/Llama-3.2-3B-F1-Resoning-Instruct:Q5

TwinkleAI/

Llama-3.2-3B-F1-Resoning-Instruct:Q5_0

435 Downloads Updated 7 months ago

F1-3B-Series (a.k.a Formosa-1 or F1) is a Traditional Chinese language model fine-tuned for Taiwan-specific tasks with strong instruction-following ability.

tools 3b

Llama-3.2-3B-F1-Resoning-Instruct:Q5_0 ... /

template

8a31c785e98a · 1.8kB

<|start_header_id|>system<|end_header_id|>

You are a function calling AI model. {{ end -}}

You are provided with function signatures within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:

<tools>

</tools>

For each function call return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:

<tool_call>

{"arguments": <args-dict>, "name": <function-name>}

</tool_call><|eot_id|>

<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>

<|start_header_id|>ipython<|end_header_id|>

<tool_response>

</tool_response>

{{- if eq $prevRole "tool" }}<|eot_id|>{{- end }}

<|start_header_id|>user<|end_header_id|>

{{ $m.Content }}<|eot_id|>{{- end }}

<|start_header_id|>assistant<|end_header_id|>

<tool_call>

{"name": "{{ $tc.Function.Name }}", "arguments": {{ json $tc.Function.Arguments }}}

</tool_call>

<|eot_id|>{{- end }}

{{- if eq $prevRole "tool" }}<|eot_id|>{{- end -}}

<|start_header_id|>assistant<|end_header_id|>

<tool_call>

{"name": "{{ .Function.Name }}", "arguments": {{ json .Function.Arguments }}}

</tool_call>