---
title: sum-small-unquantized
canonical_url: "https://www.modelscope.cn/models/mlx-community/sum-small-unquantized"
md_url: "https://www.modelscope.cn/models/mlx-community/sum-small-unquantized.md"
repository: mlx-community/sum-small-unquantized
last_updated: 2024-12-20
license: mit
model_type:
  - phi3
architectures:
  - Phi3ForCausalLM
parameters: 3.8B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 991
stars: 0
tags:
  - mlx
---

# sum-small-unquantized

> sum-small-unquantized - mlx-community 在 ModelScope 开源的模型。mlx-community/sum-small-unquantized

mlx-community/sum-small-unquantized 是 ModelScope 魔搭社区上的 3.8B 参数机器学习模型，采用 mit 许可，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/sum-small-unquantized
- **License**: mit
- **Parameters**: 3.8B
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 991
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/sum-small-unquantized

---

# mlx-community/sum-small-unquantized

The Model [mlx-community/sum-small-unquantized](https://huggingface.co/mlx-community/sum-small-unquantized) was converted to MLX format from [omi-health/sum-small](https://huggingface.co/omi-health/sum-small) using mlx-lm version **0.13.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/sum-small-unquantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```