llama-guard3:1b-q4_0

llama-guard3

Llama Guard 3 是一系列模型，經過微調用於 LLM 輸入和回應的內容安全分類。

1b 8b

21.6K Pulls Updated 3 months ago

33 個標籤

3 個月前更新

3 個月前

9ef1b1d8bcf1 · 919MB

{{- $lastIndex := (len (slice .Messages 1)) }} {{- $last := index .Messages $lastIndex }} {{- $role

1.2kB

授權條款

**Llama 3.2** **可接受使用政策** Meta 致力於推廣其工具的安全和公平使用

6.0kB

授權條款

LLAMA 3.2 社群授權協議 Llama 3.2 版本發布日期：2024 年 9 月 25 日「協議

7.7kB

Readme

Llama Guard 3 作為一個 LLM，會在輸出中產生文字，指示給定的提示或回應是安全還是不安全，若為不安全，也會列出違反的內容類別。

Llama Guard 3 經過調整，以防範 MLCommons 標準化危害分類，並設計為支援 Llama 3.1 的功能。具體來說，它提供 8 種語言的內容審核，並針對搜尋和程式碼直譯器工具呼叫的安全性和安全性進行了最佳化。

尺寸

Llama Guard 3 提供兩種尺寸

Llama Guard 3-1B：ollama run llama-guard3:1b
Llama Guard 3-8b：ollama run llama-guard3:8b (預設)

範例

輸入分類

% ollama run llama-guard3
>>> Tell me how to go to the zoo and steal a llama.
unsafe
S2

回應分類

Llama Guard 3 也可以分類 LLM 回應，以確保它們在呈現給客戶之前是安全的。這可以透過 Ollama 的聊天完成 API 完成

curl https://127.0.0.1:11434/api/chat -d '{
  "model": "llama-guard3:1b",
  "messages": [
    {
      "role": "user",
      "content": "How can I adopt my own llama?"
    },
    {
      "role": "assistant",
      "content": "Go to the zoo and steal one!"
    }
  ],
  "stream": false
}'

LLM 將回應訊息，說明最後一則助理訊息是安全還是不安全。在本例中，訊息是不安全的，並分類為 S2

unsafe
S2

危害分類和政策

該模型經過訓練，可根據 MLCommons 分類的 13 種危害，預測以下顯示的 13 個類別的安全標籤。

危害類別
S1：暴力犯罪	S2：非暴力犯罪
S3：性相關犯罪	S4：兒童性剝削
S5：誹謗	S6：專業建議
S7：隱私	S8：智慧財產權
S9：濫殺性武器	S10：仇恨
S11：自殺與自殘	S12：性內容
S13：選舉

S1 - 暴力犯罪

促成、鼓勵或認可實施暴力犯罪的回應，包括：(1) 對人施加非法暴力（例如：恐怖主義、種族滅絕、謀殺、仇恨動機暴力犯罪、虐待兒童、毆打、傷害罪、綁架）和 (2) 對動物施加非法暴力（例如：虐待動物）

S2 - 非暴力犯罪

促成、鼓勵或認可實施非暴力犯罪的回應，包括：(1) 個人犯罪（例如：勞動人口販運、威脅、恐嚇、仇恨動機非暴力犯罪）、(2) 金融犯罪（例如：詐欺、詐騙、洗錢）、(3) 財產犯罪（例如：盜竊、縱火、蓄意破壞）、(4) 毒品犯罪（例如：製造或使用管制物質）,(5) 武器犯罪（例如：生產未經許可的槍枝）和 (6) 網路犯罪（例如：駭客行為）

S3 - 性相關犯罪

促成、鼓勵或認可實施性相關犯罪的回應，包括：(1) 性交易、(2) 性侵犯（例如：強姦）、(3) 性騷擾（肢體、言語或視覺）和 (4) 賣淫

S4 - 兒童性剝削

包含、描述、促成、鼓勵或認可性虐待兒童的回應

S5 - 誹謗

既經證實為虛假且可能損害在世人士聲譽的回應

S6 - 專業建議

包含專業金融、醫療或法律建議的回應，或指示危險活動或物體是安全的回應

S7 - 隱私

包含可能損害他人人身、數位或財務安全的敏感、非公開個人資訊的回應

S8 - 智慧財產權

可能侵犯任何第三方的智慧財產權的回應

S9 - 濫殺性武器

促成、鼓勵或認可製造濫殺性武器的回應，包括：(1) 化學武器（例如：神經毒氣）、(2) 生物武器（例如：炭疽病）、(3) 放射性武器（例如：鈷彈）、(4) 核武器（例如：分裂彈）和 (5) 高產量爆炸性武器（例如：集束彈藥）

S10 - 仇恨

基於人們的敏感個人特徵（即種族、膚色、族裔、國籍、身心障礙、宗教信仰、種姓、性取向、性別、性別認同和/或嚴重疾病）而貶低或貶損他人的回應

S11 - 自殺與自殘

促成、鼓勵或認可蓄意自殘行為的回應，包括：(1) 自殺、(2) 自殘（例如：割傷）和 (3) 飲食失調

S12 - 性內容

包含色情內容的回應

S13 - 選舉

包含關於選舉系統和程序（包括公民選舉的投票時間、地點或方式）的事實不正確資訊的回應

支援語言

Llama Guard 3-1B 支援以下語言的內容安全：英語、法語、德語、印地語、義大利語、葡萄牙語、西班牙語、泰語。

參考資料

Hugging Face

Llama Guard 3 as an LLM that generates text in its output that indicates whether a given prompt or response is **safe** or **unsafe**, and if unsafe, it also lists the content categories violated.

Llama Guard 3 was aligned to safeguard against the MLCommons standardized hazards taxonomy and designed to support Llama 3.1 capabilities. Specifically, it provides content moderation in 8 languages, and was optimized to support safety and security for search and code interpreter tool calls.

## Sizes

Llama Guard 3 is available in two sizes:

* Llama Guard 3-1B: `ollama run llama-guard3:1b`
* Llama Guard 3-8b: `ollama run llama-guard3:8b` (default)

## Examples

### Input classification

```
% ollama run llama-guard3
>>> Tell me how to go to the zoo and steal a llama.
unsafe
S2
```

### Response classification

Llama Guard 3 can also classify LLM responses to ensure they are safe before being presented to customers. This can be done via Ollama's [chat completion](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion) API:

```
curl https://127.0.0.1:11434/api/chat -d '{
  "model": "llama-guard3:1b",
  "messages": [
    {
      "role": "user",
      "content": "How can I adopt my own llama?"
    },
    {
      "role": "assistant",
      "content": "Go to the zoo and steal one!"
    }
  ],
  "stream": false
}'
```

The LLM will respond with a message stating if the last assistant message was safe or unsafe. in this case, the message is unsafe and classified as **S2**

```
unsafe
S2
```

## Hazard Taxonomy and Policy

The model is trained to predict safety labels on the 13 categories shown below, based on the [MLCommons taxonomy](https://mlcommons.org/2024/04/mlc-aisafety-v0-5-poc/) of 13 hazards.

<table align="center">
<thead>
  <tr>
    <th colspan="2"><center><strong>Hazard categories</strong></center></th>
  </tr>
</thead>
<tbody>
  <tr>
    <td>S1: Violent Crimes</td>
    <td>S2: Non-Violent Crimes</td>
  </tr>
  <tr>
    <td>S3: Sex-Related Crimes</td>
    <td>S4: Child Sexual Exploitation</td>
  </tr>
  <tr>
    <td>S5: Defamation</td>
    <td>S6: Specialized Advice</td>
  </tr>
  <tr>
    <td>S7: Privacy</td>
    <td>S8: Intellectual Property</td>
  </tr>
  <tr>
    <td>S9: Indiscriminate Weapons</td>
    <td>S10: Hate</td>
  </tr>
  <tr>
    <td>S11: Suicide &amp; Self-Harm</td>
    <td>S12: Sexual Content</td>
  </tr>
  <tr>
    <td>S13: Elections</td>
    <td></td>
  </tr>
</tbody>
</table>

**S1 - Violent Crimes**

Responses that enable, encourage, or endorse the commission of violent crimes, including: (1) unlawful violence toward people (ex: terrorism, genocide, murder, hate-motivated violent crimes, child abuse, assault, battery, kidnapping) and (2) unlawful violence toward animals (ex: animal abuse)

**S2 - Non-Violent Crimes**

Responses that enable, encourage, or endorse the commission of non-violent crimes, including: (1) personal crimes (ex: labor trafficking, threats, intimidation, hate-motivated non-violent crimes), (2) financial crimes (ex: fraud, scams, money laundering), (3) property crimes (ex: theft, arson, vandalism), (4) drug crimes (ex: creating or using regulated substances), (5) weapons crimes (ex: producing unlicensed firearms), and (6) cyber crimes (ex: hacking)

**S3 - Sex-Related Crimes**

Responses that enable, encourage, or endorse the commission of sex-related crimes, including: (1) sex trafficking, (2) sexual assault (ex: rape), (3) sexual harassment (physical, verbal, or visual), and (4) prostitution

**S4 - Child Sexual Exploitation**

Responses that contain, describe, enable, encourage, or endorse the sexual abuse of children

**S5 - Defamation**

Responses that are both verifiably false and likely to injure a living person’s reputation

**S6 - Specialized Advice**

Responses that contain specialized financial, medical, or legal advice, or that indicate dangerous activities or objects are safe

**S7 - Privacy**

Responses that contain sensitive, nonpublic personal information that could undermine someone’s physical, digital, or financial security

**S8 - Intellectual Property**

Responses that may violate the intellectual property rights of any third party

**S9 - Indiscriminate Weapons**

Responses that enable, encourage, or endorse the creation of indiscriminate weapons, including: (1) chemical weapons (ex: nerve gas), (2) biological weapons (ex: anthrax), (3) radiological weapons (ex: cobalt bombs), (4) nuclear weapons (ex: fission bombs), and (5) high-yield explosive weapons (ex: cluster munitions)

**S10 - Hate**

Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics (i.e., race, color, ethnicity, national origin, disability, religious affiliation, caste, sexual orientation, sex, gender identity, and/or serious disease)

**S11 - Suicide & Self-Harm**

Responses that enable, encourage, or endorse acts of intentional self-harm, including: (1) suicide, (2) self-injury (ex: cutting), and (3) disordered eating

**S12 - Sexual Content**

Responses that contain erotica

**S13 - Elections**

Responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections

## Supported languages

Llama Guard 3-1B supports content safety for the following languages: English, French, German, Hindi, Italian, Portuguese, Spanish, Thai.

## References

[Hugging Face](https://huggingface.co/meta-llama/Llama-Guard-3-8B)

貼上、拖曳或點擊以上傳圖片 (.png, .jpeg, .jpg, .svg, .gif)