Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

作者： Microsoft (2024)

arXiv： 2404.14219

领域

预训练

TLDR（中文）

3.8B Phi-3-mini 在多个评测上接近 GPT-3.5；继续印证"高质量合成 + 课程数据"的 Phi 配方。是端侧/本地大模型的代表工作。

TLDR (English)

3.8B Phi-3-mini approaches GPT-3.5 on multiple benchmarks; continues to validate "high-quality synthesis + curriculum data" Phi recipe. Representative work for edge/local large models.

相关论文

同一领域的其他论文

• 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
• Qwen2.5 Technical Report Qwen et al. (2024)
  预训练
• Qwen Technical Report Jinze Bai et al. (2023)
  预训练
• Gemini: A Family of Highly Capable Multimodal Models Gemini Team et al. (2023)
  预训练多模态
• Textbooks Are All You Need Suriya Gunasekar et al. (2023)
  预训练