Phi-3.5-MoE-instruct
Maintainer: microsoft
470
🐍
| Property | Value |
|---|---|
| Run this model | Run on HuggingFace |
| API spec | View on HuggingFace |
| Github link | No Github link provided |
| Paper link | No paper link provided |
Create account to get full access
Model overview
The Phi-3.5-MoE-instruct is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available documents - with a focus on very high-quality, reasoning dense data. The model supports multilingual and comes with 128K context length (in tokens). The model underwent a rigorous enhancement process, incorporating supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
The Phi-3.5-MoE-instruct model is part of the Phi-3 model family, which also includes the Phi-3.5-mini-instruct and Phi-3.5-vision-instruct models.
Model inputs and outputs
Inputs
- Text: The model is best suited for prompts using the chat format.
Outputs
- Generated text: The model generates text in response to the input.
Capabilities
The Phi-3.5-MoE-instruct model is designed for strong reasoning, especially in areas like code, math, and logic. It performs well in memory/compute constrained environments and latency bound scenarios.
What can I use it for?
The Phi-3.5-MoE-instruct model is intended for commercial and research use in multiple languages. It can be used as a building block for general purpose AI systems and applications that require memory/compute constrained environments, latency bound scenarios, and strong reasoning capabilities.
Things to try
You can try the Phi-3.5-MoE-instruct model using the Try It link provided. This allows you to interactively experiment with the model and see its capabilities in action.
This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!
Related Models
⚙️
Phi-3.5-vision-instruct
457
The Phi-3.5-vision-instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include synthetic data and filtered publicly available websites, with a focus on very high-quality, reasoning-dense data both on text and vision. It belongs to the Phi-3 model family, and the multimodal version can support a 128K context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures. Model inputs and outputs Inputs Text**: The model can take text input using a chat format. Images**: The model can process single images or multiple images/video frames for tasks like image comparison and multi-image/video summarization. Outputs Generated text**: The model generates relevant text in response to the input prompt. Capabilities The Phi-3.5-vision-instruct model provides capabilities for general purpose AI systems and applications with visual and text input requirements. Key use cases include memory/compute constrained environments, latency-bound scenarios, general image understanding, optical character recognition, chart and table understanding, multiple image comparison, and multi-image or video clip summarization. What can I use it for? The Phi-3.5-vision-instruct model is intended for broad commercial and research use in English. It can be used as a building block for generative AI powered features, accelerating research on language and multimodal models. Some potential use cases include: Developing AI assistants with visual understanding capabilities Automating document processing tasks like extracting insights from charts and tables Enabling multi-modal interfaces for product search and recommendation systems Things to try The Phi-3.5-vision-instruct model's multi-frame image understanding and reasoning capabilities allow for interesting applications like detailed image comparison, multi-image summarization, and optical character recognition. Developers could explore leveraging these abilities to build novel AI-powered features for their products and services.
Updated Invalid Date
🤿
Phi-3-medium-128k-instruct
295
The Phi-3-medium-128k-instruct is a 14B parameter, lightweight, state-of-the-art open model developed by Microsoft. It was trained on synthetic data and filtered publicly available websites, with a focus on high-quality and reasoning-dense properties. The model belongs to the Phi-3 family, which also includes Phi-3-mini-128k-instruct and Phi-3-mini-4k-instruct, differing in parameter size and context length. The model underwent a post-training process that incorporated supervised fine-tuning and direct preference optimization to enhance its instruction following and safety. When evaluated on benchmarks testing common sense, language understanding, math, code, long context, and logical reasoning, the Phi-3-medium-128k-instruct demonstrated robust and state-of-the-art performance among models of similar and larger sizes. Model inputs and outputs Inputs Text**: The Phi-3-medium-128k-instruct model is best suited for text-based prompts, particularly those using a chat format. Outputs Generated text**: The model generates relevant and coherent text in response to the input prompt. Capabilities The Phi-3-medium-128k-instruct model showcases strong reasoning abilities across a variety of domains, including common sense, language understanding, mathematics, coding, and logical reasoning. For example, it can provide step-by-step solutions to math problems, generate code to implement algorithms, and engage in multi-turn conversations to demonstrate its understanding of complex topics. What can I use it for? The Phi-3-medium-128k-instruct model is intended for broad commercial and research use cases that require memory/compute-constrained environments, latency-bound scenarios, and strong reasoning capabilities. It can be used as a building block for developing generative AI-powered features, such as question-answering systems, code generation tools, and educational applications. Things to try One interesting aspect of the Phi-3-medium-128k-instruct model is its ability to handle long-form context. Try providing the model with a multi-paragraph prompt and see how it maintains coherence and relevance in its generated response. You can also experiment with using the model for specific tasks, such as translating technical jargon into plain language or generating step-by-step explanations for complex concepts.
Updated Invalid Date
🛠️
Phi-3-small-128k-instruct
116
The Phi-3-small-128k-instruct is a 7B parameter, lightweight, state-of-the-art open model trained by Microsoft. It belongs to the Phi-3 family of models, which includes variants with different context lengths such as the Phi-3-small-8k-instruct and Phi-3-mini-128k-instruct. The model was trained on a combination of synthetic data and filtered publicly available websites, with a focus on high-quality and reasoning-dense properties. After initial training, the model underwent a post-training process that incorporated both supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures. When evaluated against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, the Phi-3-small-128k-instruct demonstrated robust and state-of-the-art performance among models of the same size and next size up. Model inputs and outputs Inputs Text**: The Phi-3-small-128k-instruct model is best suited for prompts using the chat format, where the input is provided as text. Outputs Generated text**: The model generates text in response to the input prompt. Capabilities The Phi-3-small-128k-instruct model showcases strong reasoning abilities, particularly in areas like code, math, and logic. It performs well on benchmarks evaluating common sense, language understanding, and logical reasoning. The model is also designed to be lightweight and efficient, making it suitable for memory/compute-constrained environments and latency-bound scenarios. What can I use it for? The Phi-3-small-128k-instruct model is intended for broad commercial and research use in English. It can be used as a building block for general-purpose AI systems and applications that require strong reasoning capabilities, such as: Memory/compute-constrained environments Latency-bound scenarios AI systems that need to excel at tasks like coding, math, and logical reasoning Microsoft has also released other models in the Phi-3 family, such as the Phi-3-mini-128k-instruct and Phi-3-medium-128k-instruct, which may be better suited for different use cases based on their size and capabilities. Things to try One interesting aspect of the Phi-3-small-128k-instruct model is its strong performance on benchmarks evaluating logical reasoning and math skills. Developers could explore using this model as a foundation for building AI systems that need to tackle complex logical or mathematical problems, such as automated theorem proving, symbolic reasoning, or advanced question-answering. Another area to explore is the model's ability to follow instructions and adhere to safety guidelines. Developers could investigate how the model's instruction-following and safety-conscious capabilities could be leveraged in applications that require reliable and trustworthy AI assistants, such as in customer service, education, or sensitive domains.
Updated Invalid Date
🔍
Phi-3-small-8k-instruct
108
The Phi-3-small-8k-instruct is a 7B parameter, lightweight, state-of-the-art open model from Microsoft. It is part of the Phi-3 family of models, which includes variants with different context lengths - 8K and 128K. The Phi-3 models are trained on a combination of synthetic data and filtered public websites, with a focus on high-quality and reasoning-dense properties. The Phi-3-small-8k-instruct model has undergone a post-training process that incorporates both supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures. When evaluated on benchmarks testing common sense, language understanding, math, code, long context, and logical reasoning, the model demonstrated robust and state-of-the-art performance among models of similar size. Model inputs and outputs Inputs Text prompts, best suited for the chat format Outputs Generated text responses to the input prompts Capabilities The Phi-3-small-8k-instruct model excels at tasks that require strong reasoning, such as math, coding, and logical analysis. It can provide detailed and coherent responses across a wide range of topics. What can I use it for? The Phi-3-small-8k-instruct model is intended for broad commercial and research use in English. It can be used in general-purpose AI systems and applications that require memory/compute constrained environments, low-latency scenarios, or robust reasoning capabilities. The model can accelerate research on language and multimodal models, and serve as a building block for generative AI-powered features. Things to try One interesting aspect of the Phi-3-small-8k-instruct model is its ability to provide step-by-step explanations and solutions for math and coding problems. You can try prompting the model with math equations or coding challenges and observe how it breaks down the problem and walks through the solution. Another interesting area to explore is the model's language understanding and common sense reasoning capabilities. You can provide it with prompts that require an understanding of the physical world, social norms, or abstract concepts, and see how it responds.
Updated Invalid Date