Microsoft Phi-3.5 launched: A more competitive AI model
Microsoft has just officially announced the release of a new series of small language models called Phi-3.5, including three variants Phi-3.5-vision, Phi-3.5-MoE and Phi-3.5-mini.
These lightweight AI language models are built on aggregated data and filtered public web pages, supporting 128K token context lengths. All new Phi-3.5 models are now available on Hugging Face under the MIT license.
Phi-3.5-MoE: A groundbreaking combination
The Phi-3.5-MoE stands out as the first model in Microsoft's Phi family that can take advantage of Mixture of Experts (MoE) technology. This 16 x 3.8 billion parameter MoE model enabled only 6.6 billion parameters and was trained on 4.9T tokens using 512 H100 GPU systems. In today's popular AI standards, Phi-3.5-MoE outperforms Llama-3.1 8B, Gemma-2-9B and Gemini-1.5-Flash, and is close to the current leading model GPT-4o-mini .
Phi-3.5-mini: Compact and Powerful
The Phi-3.5-mini is a 3.8 billion parameter model, surpassing the Llama3.1 8B or Mistral 7B, and even competing with the Mistral NeMo 12B. It is trained on 3.4T tokens using 512 H100 GPUs. With only 3.8B active parameters, this model is competitive on multilingual tasks compared to LLMs with more active parameters. Additionally, Phi-3.5-mini now supports 128K context length, while main competitor Gemma-2 only supports 8K.
Phi-3.5-vision: Enhanced multi-frame image processing capabilities
Phi-3.5-vision is a 4.2 billion parameter model trained on 500B tokens using 256 A100 GPUs. This model now supports multi-frame image understanding and inference. Phi-3.5-vision improved performance on MMMU (from 40.2 to 43.0), MMBench (from 80.5 to 81.9) and TextVQA document processing benchmark (from 70.9 to 72.0).
Microsoft plans to share more details about the Phi-3.5 model line this month, primarily showcasing advances in AI model performance and capabilities. With a focus on lightweight design and multimodal understanding, the Phi-3.5 family of models can be applied more widely across a variety of AI applications.
You've just finished reading the article "Microsoft Phi-3.5 launched: A more competitive AI model" edited by the TipsMake team. You can save microsoft-phi35-launched-a-more-competitive-ai-model.pdf to your computer here to read later or print it out. We hope this article has provided you with many useful tech tips and tricks. You can search for similar articles on tips and guides. Thank you for reading and for following us regularly.
- OpenAI Announces o3 Pro, Its Smartest Reasoning Model Ever
- Hosted App Model, a great feature of Windows 10 2004
- Microsoft suddenly launched Windows 11 VMs exclusively for developers
- Baidu introduces the AI model Ernie 4.0 Turbo with many notable upgrades
- Microsoft integrates Model Context Protocol (MCP) into Windows 11, turning the operating system into an autonomous AI platform
- Microsoft launched a Skype for Web beta
- Acer launched the Chromebook C720 for only $ 249
- How to Identify Samsung Phone Model
- HP ProBook 4310s at competitive prices
- Please experience 'ChatGPT's grandfather' on Excel
- Lenovo launched the art laptop model
- Understanding the OSI Model (Network Knowledge Part 17)
- Lenovo launches G-series laptops at competitive prices
- DeepSeek 'lied' about the cost of developing AI chatbot?