ApX 标志

趋近智

Phi-4-Mini

参数

3.8B

上下文长度

128K

模态

Text

架构

Dense

许可证

MIT

发布日期

27 Feb 2025

知识截止

Jun 2024

技术规格

注意力结构

Grouped-Query Attention

隐藏维度大小

3072

层数

32

注意力头

24

键值头

8

激活函数

-

归一化

-

位置嵌入

ROPE

系统要求

不同量化方法和上下文大小的显存要求

Phi-4-Mini

Microsoft Phi-4-Mini is a lightweight, open model from the Phi-4 family, engineered to operate efficiently in resource-constrained environments. This model is constructed from a combination of high-quality synthetic data and filtered public web content, with a particular emphasis on data dense in reasoning. Its core architecture is a dense, decoder-only Transformer, optimized with techniques such as grouped-query attention (GQA) and LongRoPE positional encoding to enhance inference speed and manage extended context lengths. The model incorporates an expanded vocabulary of 200,064 tokens, facilitating broad multilingual support.

Key advancements in Phi-4-Mini include an enhancement process that integrates supervised fine-tuning (SFT) and direct preference optimization (DPO), along with Reinforcement Learning from Human Feedback (RLHF) for robust instruction adherence and safety measures. This training methodology enables the model to exhibit strong reasoning capabilities, particularly in mathematical and logical tasks, and supports advanced functions such as function calling. The design prioritizes computational efficiency and low-latency performance, making it suitable for deployment in scenarios where memory and processing power are limited.

The intended use cases for Phi-4-Mini span general-purpose AI systems and applications that require strong reasoning in memory or compute-constrained environments, or those with latency-bound requirements. It is designed to accelerate research in language models and serve as a foundational building block for generative AI features. The model's compact size and optimized architecture allow for deployment on edge devices, including various mobile operating systems, by leveraging tools such as Microsoft Olive and the ONNX GenAI Runtime.

关于 Phi-4

The Microsoft Phi-4 model family comprises small language models prioritizing efficient, high-capability reasoning. Its development emphasizes robust data quality and sophisticated synthetic data integration. This approach enables enhanced performance and on-device deployment capabilities.


其他 Phi-4 模型

评估基准

排名适用于本地LLM。

排名

#40

基准分数排名

Graduate-Level QA

GPQA

0.52

12

Professional Knowledge

MMLU Pro

0.53

21

General Knowledge

MMLU

0.25

36

排名

排名

#40

编程排名

-

GPU 要求

完整计算器

选择模型权重的量化方法

上下文大小:1024 个令牌

1k
63k
125k

所需显存:

推荐 GPU