HomeModelsText Generationmicrosoft/phi-4
P

microsoft/phi-4

Text Generation·microsoft· 846.7K· 2.3K
transformers mit 14.7B params arxiv:2412.08905

-------------------------------------------------------------------------------------------------------- Developers Microsoft Research Description phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. Th

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull microsoft/phi-4

Model details

Task
Text Generation
Provider
microsoft
Framework
transformers
Parameters
14.7B
Size
27 GB
License
mit
Downloads
846.7K
Likes
2.3K
Paper
arXiv:2412.08905
Updated
2025-11-24

About microsoft/phi-4

-------------------------------------------------------------------------------------------------------- Developers Microsoft Research Description phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.phi-4 underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures Architecture 14B parameters, dense decoder-only Transformer model Inputs Text, best suited for prompts in the chat format Context length 16K tokens GPUs 1920 H100-80G Training time 21 days Training data 9.8T tokens Outputs Generated text in response to input Dates October 2024 – November 2024 Status Static model t

Related Text Generation

Q Qwen/Qwen3-0.6B Text Generation ·751.6M params 27.8M 1.4K 🤗 HF Q Qwen/Qwen3-4B Text Generation ·4.0B params 16.4M 641 🤗 HF G openai-community/gpt2 Text Generation ·137.0M params 13.3M 3.3K 🤗 HF Q Qwen/Qwen3-8B Text Generation ·8.2B params 13.0M 1.2K 🤗 HF Q Qwen/Qwen2.5-7B-Instruct Text Generation ·7.6B params 12.8M 1.4K 🤗 HF O facebook/opt-125m Text Generation 12.3M 267 🤗 HF