一个基于 Phi-3 的 38 亿参数模型,在高质量的私有合成数据集上进行了微调,用于信息提取。

3.8b

20.1K 6 个月前

自述文件

NuMind 🔥 的结构化提取模型

NuExtract 是 phi-3-mini 的一个版本,它在一个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(少于 2000 个 tokens)和一个描述您需要提取的信息的 JSON 模板。

注意:此模型纯粹是抽取式的,因此模型输出的所有文本都与原始文本中的内容完全一致。您也可以提供输出格式的示例,以帮助模型更精确地理解您的任务。

用法

提示格式

当使用特定的提示格式来提取文本时,此模型效果最佳

### 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