基于 Phi-3 的一个 3.8B 模型,在私有的高质量合成数据集上进行了微调,用于信息提取。

3.8b

16.3K 3 个月前

自述文件

NuMind 结构提取模型 🔥

NuExtract 是 phi-3-mini 的一个版本,在私有的高质量合成数据集上进行了微调,用于信息提取。要使用该模型,请提供输入文本(不超过 2000 个 token)和描述您需要提取的信息的 JSON 模板。

注意:此模型纯粹是提取式的,因此模型输出的所有文本都与原始文本中的一样。您还可以提供输出格式示例来帮助模型更准确地理解您的任务。

用法

提示格式

此模型在使用特定提示格式提取文本时效果最佳

### Template:
{
    "Model": {
        "Name": "",
        "Number of parameters": "",
    },
    "Usage": {
        "Use case": [],
        "Licence": ""
    }
}
### Example:
{
    "Model": {
        "Name": "Llama3",
        "Number of parameters": "8 billion",
    },
    "Usage": {
        "Use case":[
			"chat",
			"code completion"
		],
        "Licence": "Meta Llama3"
    }
}
### Text:
We introduce Mistral 7B, a 7–billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms the best open 13B model (Llama 2) across all evaluated benchmarks, and the best released 34B model (Llama 1) in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license. 

Code: https://github.com/mistralai/mistral-src 
Webpage: https://mistral.ai/news/announcing-mistral-7b/

参考

Hugging Face