---
license: mit
base_model:
- inclusionAI/Ling-mini-2.0
---

## Introduction

Use https://github.com/im0qianqian/llama.cpp to quantize.

For model inference, please download our release package from this url https://github.com/im0qianqian/llama.cpp/releases .



## Quick start

```bash
# Use a local model file
llama-cli -m my_model.gguf

# Launch OpenAI-compatible API server
llama-server -m my_model.gguf
```


## Demo

![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fde26773930f07f74aaf912/MC4h9G33YjvpboRA4LPfO.png)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fde26773930f07f74aaf912/0YcuTJFLs6k9K4Sgzd-UD.png)


## PR

Let's look forward to the following PR being merged:

- [#16063 model : add BailingMoeV2 support](https://github.com/ggml-org/llama.cpp/pull/16063)
- [#16028 Add support for Ling v2](https://github.com/ggml-org/llama.cpp/pull/16028)