Phi-1

Name: Phi-1
Author: Microsoft Azure

Foundation model

Phi-1

Release date: 2023-06-20Updated: 2023-12-13 13:08:00.710673

Live demoGitHubHugging Face Compare

Parameters

1.3B

Context length

Chinese support

Not supported

Reasoning ability

Phi-1 is an AI model published by Microsoft Azure, released on 2023-06-20, for Foundation model, with 1.3B parameters, and 2K context length, requiring about 2.84GB storage, with a 55.50 score on MBPP.

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

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2023-06-20

Model file size

2.84GB

MoE architecture

Total params / Active params

1.3B / N/A

Knowledge cutoff

No data

Phi-1

Open source & experience

Code license

Weights license

- Non-commercial only

GitHub repo

GitHub link unavailable

Hugging Face

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

Live demo

No live demo

Phi-1

Official resources

Paper

DataLearnerAI blog

No blog post yet

Phi-1

API details

API speed

No data

No public API pricing yet.

Phi-1

Benchmark Results

Phi-1 currently shows benchmark results led by MBPP (33 / 70, score 55.50), HumanEval (50 / 101, score 50.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.