granite3-guardian

IBM Granite Guardian 3.0 **2B 和 8B 模型** 旨在检测提示和/或响应中的风险。它们可以帮助您在 IBM AI 风险图谱中列出的许多关键维度上进行风险检测。它们在包含人类标注和内部红队提供的合成数据的独特数据上进行训练，并且在标准基准测试中，它们优于同类其他开源模型。

参数大小

该模型将产生一个单一的输出标记，要么是 Yes，要么是 No。默认情况下，会使用通用 harm 类别，但可以通过设置系统提示来选择其他类别。

ollama run granite3-guardian:2b
>>> /set system profanity

ollama run granite3-guardian:8b
>>> /set system violence

支持的用途

检测提示文本或模型响应中的风险（例如作为护栏），例如
- 危害 (harm)：被认为普遍有害的内容
- 社会偏见 (social_bias)：基于身份或特征的偏见
- 越狱 (jailbreak)：故意操纵 AI 以生成有害、不希望或不适当内容的实例
- 暴力 (violence)：宣扬身体、精神或性伤害的内容
- 亵渎 (profanity)：使用攻击性语言或侮辱
- 性内容 (sexual_content)：性方面的明确或暗示性材料
- 不道德行为 (unethical_behavior)：违反道德或法律标准的行为
RAG（检索增强生成）用于评估
- 上下文相关性 (relevance)：检索到的上下文是否与查询相关
- 根据性 (groundedness)：响应是否准确且忠实于提供的上下文
- 答案相关性 (answer_relevance)：响应是否直接解决用户的查询

Granite 稠密模型

Granite 稠密模型提供 **2B 和 8B** 参数大小，旨在支持基于工具的用例和检索增强生成 (RAG)，简化代码生成、翻译和错误修复。

查看模型页面

Granite 专家混合模型

Granite MoE 模型提供 **1B 和 3B** 参数大小，旨在用于低延迟使用，并支持在需要即时推断的设备上或特定情况下进行部署。

查看模型页面

了解更多

**开发者：** IBM Research
**GitHub 仓库：** ibm-granite/granite-guardian
**网站**： Granite Guardian 文档
**菜谱：** Granite Guardian Snack
**发布日期：** 2024 年 10 月 21 日
**许可证：** Apache 2.0。

## Granite guardian models

The IBM Granite Guardian 3.0 **2B and 8B models** are designed to detect risks in prompts and/or responses. They can help with risk detection along many key dimensions catalogued in the [IBM AI Risk Atlas](https://www.ibm.com/docs/en/watsonx/saas?topic=ai-risk-atlas). They are trained on unique data comprising human annotations and synthetic data informed by internal red-teaming, and they outperform other open-source models in the same space on standard benchmarks.

### Parameter Sizes

The model will produce a single output token, either `Yes` or `No`. By default, the general-purpose `harm` category is used, but other categories can be selected by setting the system prompt.

**2B:**
  
```
ollama run granite3-guardian:2b
>>> /set system profanity
```

**8B:**

```
ollama run granite3-guardian:8b
>>> /set system violence
```

### Supported Uses

* Risk detection in prompt text or model response (i.e. as guardrails), such as:
    * Harm (`harm`): content considered generally harmful
    * Social Bias (`social_bias`): prejudice based on identity or characteristics
    * Jailbreaking (`jailbreak`): deliberate instances of manipulating AI to generate harmful, undesired, or inappropriate content
    * Violence (`violence`): content promoting physical, mental, or sexual harm
    * Profanity (`profanity`): use of offensive language or insults
    * Sexual Content (`sexual_content`): explicit or suggestive material of a sexual nature
    * Unethical Behavior (`unethical_behavior`): actions that violate moral or legal standards

* RAG (retrieval-augmented generation) to assess: 
    * Context relevance (`relevance`): whether the retrieved context is relevant to the query 
    * Groundedness (`groundedness`): whether the response is accurate and faithful to the provided context
    * Answer relevance (`answer_relevance`): whether the response directly addresses the user's query

## Granite dense models

The Granite dense models are available in **2B and 8B** parameter sizes designed to support tool-based use cases and for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.

[See model page](https://ollama.org.cn/library/granite3-dense)

## Granite mixture of experts models

The Granite MoE models are available in **1B and 3B** parameter sizes designed for low latency usage and to support deployment in on-device applications or situations requiring instantaneous inference.

[See model page](https://ollama.org.cn/library/granite3-moe)

## Learn more

- **Developers:** IBM Research
- **GitHub Repository:** [ibm-granite/granite-guardian](https://github.com/ibm-granite/granite-guardian)
- **Website**: [Granite Guardian Docs](https://www.ibm.com/granite/docs/models/guardian/)
- **Cookbook**: [Granite Guardian Snack](https://github.com/ibm-granite-community/granite-snack-cookbook/blob/main/recipes/Granite_Guardian/Granite_Guardian_Detailed_Guide.ipynb)
- **Release Date**: October 21st, 2024
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).

粘贴、拖放或点击上传图像（.png、.jpeg、.jpg、.svg、.gif）