granite3-guardian:8b-q6_K

IBM Granite Guardian 3.0 **2B 和 8B 模型**旨在偵測提示和/或回應中的風險。它們可以協助偵測《IBM AI 風險圖譜》中編目的許多關鍵維度中的風險。它們使用包含人工註釋和內部紅隊演練提供的合成資料的獨特資料進行訓練，並且在標準基準測試中，它們的效能優於同一領域的其他開放原始碼模型。

參數大小

此模型將產生單一輸出符記，即「Yes」或「No」。預設情況下，會使用通用「harm」類別，但可以透過設定系統提示來選擇其他類別。

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

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

支援用途

在提示文字或模型回應中進行風險偵測（即作為護欄），例如：
- 危害 (harm)：被認為通常有害的內容
- 社會偏見 (social_bias)：基於身分或特徵的偏見
- 越獄 (jailbreak)：蓄意操縱 AI 以產生有害、不良或不當內容的例子
- 暴力 (violence)：宣傳身體、精神或性傷害的內容
- 褻瀆 (profanity)：使用冒犯性語言或侮辱
- 色情內容 (sexual_content)：露骨或暗示性的性性質材料
- 不道德行為 (unethical_behavior)：違反道德或法律標準的行為
RAG（檢索增強生成）以評估
- 內容相關性 (relevance)：檢索到的內容是否與查詢相關
- 根據性 (groundedness)：回應是否準確且忠實於提供的內容
- 答案相關性 (answer_relevance)：回應是否直接解決使用者的查詢

Granite 稠密模型

Granite 稠密模型提供 **2B 和 8B** 參數大小，旨在支援基於工具的使用案例以及檢索增強生成 (RAG)，從而簡化程式碼生成、翻譯和錯誤修復。

查看模型頁面

Granite 混合專家模型

Granite MoE 模型提供 **1B 和 3B** 參數大小，專為低延遲使用而設計，並支援在裝置端應用程式或需要即時推論的情況下部署。

查看模型頁面

了解更多

開發者： IBM 研究院
GitHub 儲存庫： ibm-granite/granite-guardian
網站： Granite Guardian Docs
食譜： Granite Guardian Snack
發布日期： 2024 年 10 月 21 日
許可證： 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.dev.org.tw/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.dev.org.tw/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).

貼上、拖放或點擊以**上傳圖片** (.png, .jpeg, .jpg, .svg, .gif)