GGUF
Inference Endpoints
conversational
phi3 / README.md
Pham
rename cortexso
5d61621 verified
---
license: ms-pl
---
## Overview
The [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct), state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the 4B, 7B version in two variants 8K and 128K which is the context length (in tokens) that it can support.
## Variants
| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [mini-onnx](https://huggingface.co/cortexso/phi3/tree/mini-onnx) | `cortex run phi3:mini-onnx` |
| 2 | [mini-gguf](https://huggingface.co/cortexso/phi3/tree/mini-gguf) | `cortex run phi3:mini-gguf` |
| 3 | [medium-gguf](https://huggingface.co/cortexso/phi3/tree/medium-gguf) | `cortex run phi3:medium-gguf` |
| 4 | [medium-onnx](https://huggingface.co/cortexso/phi3/tree/medium-onnx) | `cortex run phi3:medium-onnx` |
## Use it with Jan (UI)
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
```
cortexso/phi3
```
## Use it with Cortex (CLI)
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
```
cortex run phi3
```
## Credits
- **Author:** Microsoft
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
- **Original License:** [License](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE)
- **Papers:** [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219)