微软发布HARC-Llama-3.1-8B-Instruct安全对齐模型
英文摘要
Microsoft released HARC-Llama-3.1-8B-Instruct on Hugging Face. It is a text-generation model built on Meta's Llama 3.1 8B Instruct. Repository tags indicate a focus on safety, alignment, and conversational use. The model card provides no benchmarks, training details, or specific capability claims. It is distributed under the Llama 3.1 license.
中文摘要
微软在Hugging Face上发布了HARC-Llama-3.1-8B-Instruct。该模型是基于Meta的Llama 3.1 8B Instruct构建的文本生成模型。仓库标签显示其专注安全、对齐和对话应用。模型卡片未提供基准测试、训练细节或具体能力声明。该模型以Llama 3.1许可证分发。
关键要点
Based on meta-llama/Llama-3.1-8B-Instruct, indicating a fine-tuned instruction variant.
基于meta-llama/Llama-3.1-8B-Instruct，表明是经过指令微调的变体。
Tagged with safety, alignment, and conversational, suggesting a focus on responsible dialogue.
标签包含安全、对齐和对话，暗示关注负责任的对话。
No benchmarks, paper, or detailed description accompany the release.
发布时未附有基准测试、论文或详细说明。
Released under the original Llama 3.1 license.
以原始的Llama 3.1许可证发布。