Meta Llama Guard 2 Model

**Overview** The Meta Llama Guard 2 model is a large language model (LLM) developed by Meta AI. The model provided in this listing is: - [meta_llama_guard_2_8b](https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B): an 8B parameter Llama 3-based input-output safeguard model. It can be used for classifying 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/unsafe, and if unsafe based on a policy, it also lists the violating subcategories. The model is packaged using MLflow’s transformers flavor. The Meta Llama Guard 2 model is licensed under the [Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved](https://llama.meta.com/llama3/license/). By installing this listing, you acknowledge and agree to the license. **Use cases** [meta_llama_guard_2_8b](https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B): - Meta Llama Guard 2 is an 8B parameter Meta Llama 3-based input-output safeguard model. It can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification). **Product details** The models in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for continued fine-tuning use cases. For more details, install the listing and view the provided model cards for each model.

搜集汇总

背景与挑战

背景概述

Meta Llama Guard 2模型是一个由Meta AI开发的8B参数大型语言模型，基于Llama 3构建，用于对LLM输入和输出进行内容安全分类，并标识违反策略的类别。该模型采用MLflow transformers风格打包，遵循Meta Llama 3社区许可证，可直接部署到Databricks Model Serving或用于微调任务。