---
title: Luni_StarDust-12b-v2
canonical_url: "https://www.modelscope.cn/models/mlx-community/Luni_StarDust-12b-v2"
md_url: "https://www.modelscope.cn/models/mlx-community/Luni_StarDust-12b-v2.md"
repository: mlx-community/Luni_StarDust-12b-v2
last_updated: 2024-12-19
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 3.4B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1000
stars: 0
tags:
  - chat
  - mistral
  - roleplay
  - creative-writing
  - mlx
---

# Luni_StarDust-12b-v2

> Luni_StarDust-12b-v2 - mlx-community 在 ModelScope 开源的模型。mlx-community/LuniStarDust-12b-v2

mlx-community/Luni_StarDust-12b-v2 是 ModelScope 魔搭社区上的 3.4B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Luni_StarDust-12b-v2
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 3.4B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: chat, mistral, roleplay, creative-writing, mlx
- **Downloads**: 1000
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/Luni_StarDust-12b-v2

---

# mlx-community/Luni_StarDust-12b-v2

The Model [mlx-community/Luni_StarDust-12b-v2](https://huggingface.co/mlx-community/Luni_StarDust-12b-v2) was converted to MLX format from [Luni/StarDust-12b-v2](https://huggingface.co/Luni/StarDust-12b-v2) using mlx-lm version **0.19.0**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Luni_StarDust-12b-v2")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```