---
title: gemma-2-9b-it-SimPO-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO-8bit.md"
repository: mlx-community/gemma-2-9b-it-SimPO-8bit
last_updated: 2025-07-22
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gemma2
architectures:
  - Gemma2ForCausalLM
base_model:
  - princeton-nlp/gemma-2-9b-it-SimPO
base_model_relation: quantized
parameters: 2.6B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 138
stars: 0
tags:
  - alignment-handbook
  - generated_from_trainer
  - mlx
---

# gemma-2-9b-it-SimPO-8bit

> gemma-2-9b-it-SimPO-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/gemma-2-9b-it-SimPO-8bit

mlx-community/gemma-2-9b-it-SimPO-8bit 是 ModelScope 魔搭社区上的 2.6B 参数text-generation模型，采用 mit 许可，基于 princeton-nlp/gemma-2-9b-it-SimPO 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/gemma-2-9b-it-SimPO-8bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 2.6B
- **Base model**: princeton-nlp/gemma-2-9b-it-SimPO
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: alignment-handbook, generated_from_trainer, mlx
- **Downloads**: 138
- **Stars**: 0
- **Last updated**: 2025-07-22

Source: https://www.modelscope.cn/models/mlx-community/gemma-2-9b-it-SimPO-8bit

---

# mlx-community/gemma-2-9b-it-SimPO-8bit

This model [mlx-community/gemma-2-9b-it-SimPO-8bit](https://huggingface.co/mlx-community/gemma-2-9b-it-SimPO-8bit) was
converted to MLX format from [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)
using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-9b-it-SimPO-8bit")

prompt = "hello"

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

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