Phi 3.5 mini instruct
microsoft/Phi-3.5-mini-instruct
Open Source · chat · open-weights
Open
Alert me on changes
Context
128K
Max output
4K
Weights
Open
API $/1M
$0.13 / $0.52
Modalities
text
Released
16 Aug 2024
License: mit · microsoft/Phi-3.5-mini-instruct
AI summary
● machine-written
Microsoft Phi-3.5 Mini Instruct: Open-weights chat model with 128K context
Phi-3.5 Mini Instruct is a lightweight, open-source language model from Microsoft optimized for instruction-following and reasoning in resource-constrained environments. It supports a 128K token context window with up to 4K output tokens. The model is available under MIT license with open-weights access.
What's new
- 128K token context window supports extended document processing
- Up to 4K output tokens per response
- Optimized for efficient reasoning on limited-resource devices
- Available across multiple inference providers including Azure AI Foundry
Best for
Resource-constrained environments and edge deploymentInstruction-following and conversational tasksCode generation and reasoning tasksMultilingual text generation
Source: https://huggingface.co/microsoft/Phi-3.5-mini-instruct