granite3-guardian:8b-fp16

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 Risk Atlas 中編目的許多關鍵維度的風險。它們使用獨特的資料進行訓練，這些資料包括人工註釋和內部紅隊演練提供的合成資料，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標記，即 Yes 或 No。依預設，會使用通用 harm 類別，但可以透過設定系統提示來選取其他類別。

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

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

支援用途

提示文字或模型回應中的風險偵測（即作為護欄），例如
- 危害 (harm)：一般認為有害的內容
- 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、不良或不當內容的實例
- 暴力 (violence)：宣傳肢體、精神或性傷害的內容
- 褻瀆 (profanity)：使用冒犯性語言或侮辱
- 性內容 (sexual_content)：明確或暗示性的性相關材料
- 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
- 上下文相關性 (relevance)：檢索到的上下文是否與查詢相關
- 根據性 (groundedness)：回應是否準確且忠實於提供的上下文
- 答案相關性 (answer_relevance)：回應是否直接解決使用者的查詢

Granite 密集模型

Granite 密集模型提供 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)，簡化程式碼生成、翻譯和錯誤修復。

查看模型頁面

Granite 專家混合模型

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

查看模型頁面

瞭解更多

開發人員： IBM Research
GitHub 儲存庫： ibm-granite/granite-guardian
網站： Granite Guardian 文件
Cookbook： Granite Guardian Snack
發布日期： 2024 年 10 月 21 日
授權條款： 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)