这是Llama 3 Groq工具使用模型的8B参数版本,专为高级工具使用和函数调用任务设计。
该模型专为工具使用和函数调用场景的研究与开发设计。它在涉及API交互、结构化数据操作和复杂工具使用的任务中表现出色。然而,用户应注意:
请注意,该模型对temperature和top_p采样配置非常敏感。建议从temperature=0.5, top_p=0.65开始,并根据需要进行调整。
文本提示示例:
我们想特别感谢@NousResearch,他们通过在LLM中公开和开放地探索工具使用,推动了开源工具使用的发展。
<|start_header_id|>system<|end_header_id|>
You are a function calling AI model. 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. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"name": <function-name>,"arguments": <args-dict>}
</tool_call>
Here are the available tools:
<tools> {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
},
"unit": {
"enum": [
"celsius",
"fahrenheit"
],
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
} </tools><|eot_id|><|start_header_id|>user<|end_header_id|>
What is the weather like in San Francisco?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
<tool_call>
{"id":"call_deok","name":"get_current_weather","arguments":{"location":"San Francisco","unit":"celsius"}}
</tool_call><|eot_id|><|start_header_id|>tool<|end_header_id|>
<tool_response>
{"id":"call_deok","result":{"temperature":"72","unit":"celsius"}}
</tool_response><|eot_id|><|start_header_id|>assistant<|end_header_id|>
尽管该模型专为工具使用进行了微调,但它继承了基础Llama 3模型的所有道德考量。请负责任地使用,并根据您的应用程序需求实施额外的安全措施。
该模型可通过以下途径获得:
欲了解关于负责任使用、道德考量及最新基准测试的详细信息,请参考Llama 3官方文档和Groq模型卡片。