Latest AI Insights

Model Evaluations

Model Directory

Model Comparison

Resource Center

Search blog

加载中...

DataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

Leaderboards
模型对比
Datasets

资源

Tutorials
Editorial
Tool directory

关于

关于我们
隐私政策
数据收集方法
联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款

Phi-1 - AI Model Details and Benchmarks | DataLearnerAI

Page navigation

目录

Model catalogPhi-1

PH

Phi-1

Phi-1

Release date: 2023-06-20更新于: 2023-12-13 13:08:00.710582

Live demoGitHubHugging Face Compare

Parameters

13.0亿

Context length

2K

Chinese support

Not supported

Reasoning ability

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Phi-1

Model basics

Reasoning traces

Not supported

Context length

2K tokens

Max output length

No data

Model type

基础大模型

Release date

2023-06-20

Model file size

Phi-1

Open source & experience

Code license

Microsoft Research License

Weights license

Microsoft Research License- 不可以商用

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/microsoft/phi-1

Phi-1

Official resources

Paper

Textbooks Are All You Need

DataLearnerAI blog

No blog post yet

Phi-1

API details

API speed

No data

No public API pricing yet.

Phi-1

Benchmark Results

No benchmark data to show.

Phi-1

Publisher

Microsoft Azure

View publisher details

Phi-1

Model Overview

这是微软发布的一个小规模参数的大语言模型，目的是证明使用高质量数据集和合适的模型架构，可以让小规模参数的模型也有涌现的能力。

Phi-1是一个参数仅有13亿的大语言模型，目标是代码生成。从网络上用了60亿tokens的教科书般质量的数据集以及GPT-3.5合成的10亿tokens数据集进行训练。最终，这个模型在代码生成能力上表现非凡，它的python代码生成评测结果与CodeLLaMA-34B差不多，十分让人惊叹。

不过，Phi-1是一个不能商用模型。它的编程评测结果参考我们DataLearnerAI的大模型编程排行： https://www.datalearner.com/ai-models/llm-coding-evaluation

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

DataLearner 官方微信二维码

2.84GB

MoE architecture

No

Total params / Active params

13.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

Live demo

No live demo