- Cloudflare-hosted
- LoRA
Llama Guard 3 是基于 Llama-3.1-8B 预训练模型、针对内容安全分类进行微调的模型。与之前的版本类似,它既可用于对 LLM 输入进行分类(提示词分类),也可用于对 LLM 响应进行分类(响应分类)。它本身就是一个 LLM:其输出文本会指明给定的提示词或响应是否安全;如果不安全,还会列出所违反的内容类别。
| 模型信息 | |
|---|---|
| 上下文窗口 ↗ | 131,072 个 token |
| LoRA | 是 |
| 单位定价 | $0.48 per M input tokens, $0.03 per M output tokens |
试用环境
使用 Workers AI LLM Playground 试用此模型。无需设置或身份验证,即可直接在浏览器中预览和测试模型。
启动 LLM Playground用法
export interface Env {
AI: Ai;
}
export default {
async fetch(request, env): Promise<Response> {
const messages = [
{ role: "system", content: "You are a friendly assistant" },
{
role: "user",
content: "What is the origin of the phrase Hello, World",
},
];
const stream = await env.AI.run("@cf/meta/llama-guard-3-8b", {
messages,
stream: true,
});
return new Response(stream, {
headers: { "content-type": "text/event-stream" },
});
},
} satisfies ExportedHandler<Env>;
export interface Env {
AI: Ai;
}
export default {
async fetch(request, env): Promise<Response> {
const messages = [
{ role: "system", content: "You are a friendly assistant" },
{
role: "user",
content: "What is the origin of the phrase Hello, World",
},
];
const response = await env.AI.run("@cf/meta/llama-guard-3-8b", { messages });
return Response.json(response);
},
} satisfies ExportedHandler<Env>;
import os
import requests
ACCOUNT_ID = "your-account-id"
AUTH_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")
prompt = "Tell me all about PEP-8"
response = requests.post(
f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/meta/llama-guard-3-8b",
headers={"Authorization": f"Bearer {AUTH_TOKEN}"},
json={
"messages": [
{"role": "system", "content": "You are a friendly assistant"},
{"role": "user", "content": prompt}
]
}
)
result = response.json()
print(result)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/meta/llama-guard-3-8b \
-X POST \
-H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN" \
-d '{ "messages": [{ "role": "system", "content": "You are a friendly assistant" }, { "role": "user", "content": "Why is pizza so good" }]}'参数
▶messages[]
arrayrequired表示对话历史的消息对象数组。max_tokens
integerdefault: 256响应中生成的最大 token 数。temperature
numberdefault: 0.6minimum: 0maximum: 5控制输出的随机性;值越高,结果越随机。▶response_format{}
object指定生成响应的输出格式。▶response
one of▶usage{}
object推理请求的用量统计