|
--- |
|
license: mit |
|
pipeline_tag: text-generation |
|
tags: |
|
- cortex.cpp |
|
--- |
|
## Overview |
|
|
|
**Qwen Labs** developed and released the [Qwen2.5-Coder](https://huggingface.co/Qwen) model, a state-of-the-art language model tailored for code generation, understanding, and completion tasks. Featuring a 2.5B parameter dense Transformer architecture, Qwen2.5-Coder is designed to assist developers and researchers by generating high-quality code snippets, providing algorithm explanations, and completing coding prompts with accuracy. The model was trained on a diverse blend of programming languages and frameworks using carefully filtered code datasets to ensure precision and relevance. It leverages advanced fine-tuning techniques and rigorous safety measures to optimize instruction adherence and deliver reliable, contextually aware outputs. Released in November 2024, Qwen2.5-Coder offers an effective tool for software development, academic research, and programming education. |
|
|
|
## Variants |
|
|
|
| No | Variant | Cortex CLI command | |
|
| --- | --- | --- | |
|
| 1 | [gguf](https://huggingface.co/cortexso/qwen2.5-coder/tree/main) | `cortex run qwen2.5-coder` | |
|
|
|
## Use it with Jan (UI) |
|
|
|
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) |
|
2. Use in Jan model Hub: |
|
```text |
|
cortexso/qwen2.5-coder |
|
``` |
|
|
|
## Use it with Cortex (CLI) |
|
|
|
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) |
|
2. Run the model with command: |
|
```bash |
|
cortex run qwen2.5-coder |
|
``` |
|
|
|
## Credits |
|
|
|
- **Author:** Qwen Labs |
|
- **Converter:** [Homebrew](https://www.homebrew.ltd/) |
|
- **Original License:** [License](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/LICENSE) |
|
- **Papers:** [Qwen2.5-Coder Technical Report](https://arxiv.org/abs/2409.12186) |
