Llama 2: Open Foundation and Fine-Tuned Chat Models

作者： Meta AI (2023)

arXiv： 2307.09288

领域

预训练对齐

TLDR（中文）

第一个商用许可的高质量开源 chat 模型，并公开了 RLHF 配方（PPO + GAtt）。直接把开源生态推进到"接近 ChatGPT 体验"的阶段。

TLDR (English)

First commercially licensed high-quality open-source chat model, publicly shares RLHF recipe (PPO + GAtt). Directly advances open-source ecosystem to "near ChatGPT experience" stage.

相关论文

同一领域的其他论文

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning DeepSeek-AI (2025)
  推理能力对齐
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Microsoft (2024)
  预训练
• Yi: Open Foundation Models by 01.AI 01. AI et al. (2024)
  预训练
• The Llama 3 Herd of Models Meta AI (2024)
  预训练
• KTO: Model Alignment as Prospect Theoretic Optimization Kawin Ethayarajh et al. (2024)
  对齐
• Qwen2.5 Technical Report Qwen et al. (2024)
  预训练