LLM ReferenceLLM Reference

Phi-1

Microsoft ResearchMITOpen Source
2 models2023From $0.07/1M input

About

The Phi-1 family of large language models (LLMs), developed by Microsoft, comprises several models designed for specific tasks, primarily focusing on code generation and reasoning. Phi-1, the initial model in the family, is a transformer-based model with 1.3 billion parameters, specializing in basic Python coding 18. Its training utilized a blend of "textbook quality" data sourced from the web and synthetic data generated using GPT-3.5 18. Despite its relatively small size compared to other LLMs, Phi-1 demonstrates impressive accuracy, exceeding 50% on the HumanEval benchmark for simple Python coding tasks 18. Subsequent models in the Phi family, such as Phi-1.5 and Phi-2, build upon this foundation, expanding capabilities to encompass broader natural language tasks while maintaining a focus on efficiency and high-quality data 911. These models showcase Microsoft's research into creating smaller, more efficient LLMs that rival the performance of much larger models 29.

Specifications(2 models)

Phi-1 model specifications comparison
ModelReleasedParameters
Phi-1.52023-091.3B
Phi-12023-061.3B

Available From(1 provider)

Pricing

Phi-1 model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Phi-1.5Microsoft Foundry$0.07$0.07Provisioned

Frequently Asked Questions

What is Phi-1?
The Phi-1 family of large language models (LLMs), developed by Microsoft, comprises several models designed for specific tasks, primarily focusing on code generation and reasoning. Phi-1, the initial model in the family, is a transformer-based model with 1.3 billion parameters, specializing in basic Python coding 18. Its training utilized a blend of "textbook quality" data sourced from the web and synthetic data generated using GPT-3.5 18. Despite its relatively small size compared to other LLMs, Phi-1 demonstrates impressive accuracy, exceeding 50% on the HumanEval benchmark for simple Python coding tasks 18. Subsequent models in the Phi family, such as Phi-1.5 and Phi-2, build upon this foundation, expanding capabilities to encompass broader natural language tasks while maintaining a focus on efficiency and high-quality data 911. These models showcase Microsoft's research into creating smaller, more efficient LLMs that rival the performance of much larger models 29.
How many models are in the Phi-1 family?
The Phi-1 family contains 2 models.
What is the latest Phi-1 model?
The latest model is Phi-1.5, released in 2023-09.
How much does Phi-1 cost?
Phi-1 models are available at $0.07/1M input tokens through providers like Microsoft Foundry.

Models(2)