---
title: ALMA-13B-R-4bit-mlx
canonical_url: "https://www.modelscope.cn/models/mlx-community/ALMA-13B-R-4bit-mlx"
md_url: "https://www.modelscope.cn/models/mlx-community/ALMA-13B-R-4bit-mlx.md"
repository: mlx-community/ALMA-13B-R-4bit-mlx
last_updated: 2024-12-19
license: mit
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 2.2B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 3646
stars: 0
tags:
  - mlx
---

# ALMA-13B-R-4bit-mlx

> ALMA-13B-R-4bit-mlx - mlx-community 在 ModelScope 开源的模型。mlx-community/ALMA-13B-R-4bit-mlx This model was converted to MLX format from haoranxu/ALMA-13B-R. Refer to the original model card for more details on the model. Use with mlx

mlx-community/ALMA-13B-R-4bit-mlx 是 ModelScope 魔搭社区上的 2.2B 参数机器学习模型，采用 mit 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/ALMA-13B-R-4bit-mlx
- **License**: mit
- **Parameters**: 2.2B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 3646
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/ALMA-13B-R-4bit-mlx

---

# mlx-community/ALMA-13B-R-4bit-mlx
This model was converted to MLX format from [`haoranxu/ALMA-13B-R`]().
Refer to the [original model card](https://huggingface.co/haoranxu/ALMA-13B-R) 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/ALMA-13B-R-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```