Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
## Overview
|
| 5 |
+
|
| 6 |
+
Phi-4 model, a state-of-the-art 14B parameter Transformer designed for advanced reasoning, conversational AI, and high-quality text generation. Built on a mix of synthetic datasets, filtered public domain content, academic books, and Q&A datasets, Phi-4 ensures exceptional performance through data quality and alignment. It features a 16K token context length, trained on 9.8T tokens over 21 days using 1920 H100-80G GPUs. Phi-4 underwent rigorous fine-tuning and preference optimization to enhance instruction adherence and safety. Released on December 12, 2024, it represents a static model with data cutoff as of June 2024, suitable for diverse applications in research and dialogue systems.
|
| 7 |
+
|
| 8 |
+
## Variants
|
| 9 |
+
|
| 10 |
+
| No | Variant | Cortex CLI command |
|
| 11 |
+
| --- | --- | --- |
|
| 12 |
+
| 1 | [gguf](https://huggingface.co/cortexso/phi-4/tree/main) | `cortex run phi-4` |
|
| 13 |
+
|
| 14 |
+
## Use it with Jan (UI)
|
| 15 |
+
|
| 16 |
+
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
|
| 17 |
+
2. Use in Jan model Hub:
|
| 18 |
+
```text
|
| 19 |
+
cortexso/phi-4
|
| 20 |
+
```
|
| 21 |
+
|
| 22 |
+
## Use it with Cortex (CLI)
|
| 23 |
+
|
| 24 |
+
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
|
| 25 |
+
2. Run the model with command:
|
| 26 |
+
```bash
|
| 27 |
+
cortex run phi-4
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
## Credits
|
| 31 |
+
|
| 32 |
+
- **Author:** Microsoft Research
|
| 33 |
+
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
|
| 34 |
+
- **Original License:** [License](https://huggingface.co/microsoft/phi-4/blob/main/LICENSE)
|
| 35 |
+
- **Papers:** [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)
|