---
title: MiniCPM-2B-dpo-bf16-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-2B-dpo-bf16-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-2B-dpo-bf16-4bit.md"
repository: mlx-community/MiniCPM-2B-dpo-bf16-4bit
last_updated: 2024-12-19
model_type:
  - minicpm
architectures:
  - MiniCPMForCausalLM
parameters: 470.1M
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1182
stars: 0
tags:
  - MiniCPM
  - ModelBest
  - THUNLP
  - mlx
---

# MiniCPM-2B-dpo-bf16-4bit

> MiniCPM-2B-dpo-bf16-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/MiniCPM-2B-dpo-bf16-4bit This model was converted to MLX format from Isaak-Carter/MiniCPM-2B-dpo-bf16-safetensors using mlx-lm version 0.12.1. Refer to the original model card for more…

mlx-community/MiniCPM-2B-dpo-bf16-4bit 是 ModelScope 魔搭社区上的 470.1M 参数机器学习模型，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/MiniCPM-2B-dpo-bf16-4bit
- **Parameters**: 470.1M
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: MiniCPM, ModelBest, THUNLP, mlx
- **Downloads**: 1182
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/MiniCPM-2B-dpo-bf16-4bit

---

# mlx-community/MiniCPM-2B-dpo-bf16-4bit
This model was converted to MLX format from [`Isaak-Carter/MiniCPM-2B-dpo-bf16-safetensors`]() using mlx-lm version **0.12.1**.
Refer to the [original model card](https://huggingface.co/Isaak-Carter/MiniCPM-2B-dpo-bf16-safetensors) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniCPM-2B-dpo-bf16-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```