Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it 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.
| 信号 | 强度 | 权重 | 影响 |
|---|---|---|---|
| Context Windowjust now | 81 | 15% | +12.2 |
| Recencyjust now | 59 | 15% | +8.8 |
| Capabilitiesjust now | 17 | 30% | +5.0 |
| Output Capacityjust now | 20 | 15% | +3.0 |
| Pricingjust now | 0 | 25% | +0.0 |
社区和从业者反馈在基准测试和价格之上增加了真实世界的信号。
Share your experience with Llama Guard 3 8B and help the community make better decisions.
成本估算器
每月比类别平均节省$42.22