---
title: aya-23-8B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/aya-23-8B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/aya-23-8B-4bit.md"
repository: mlx-community/aya-23-8B-4bit
last_updated: 2024-12-19
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - cohere
architectures:
  - CohereForCausalLM
parameters: 1.3B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
  - el
  - fa
  - pl
  - id
  - cs
  - he
  - hi
  - nl
  - ro
  - ru
  - tr
  - uk
  - vi
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1012
stars: 0
tags:
  - mlx
---

# aya-23-8B-4bit

> aya-23-8B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/aya-23-8B-4bit

mlx-community/aya-23-8B-4bit 是 ModelScope 魔搭社区上的 1.3B 参数text-generation模型，采用 cc-by-nc-4.0 许可，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/aya-23-8B-4bit
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Parameters**: 1.3B
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 1012
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/aya-23-8B-4bit

---

# mlx-community/aya-23-8B-4bit

The Model [mlx-community/aya-23-8B-4bit](https://huggingface.co/mlx-community/aya-23-8B-4bit) was converted to MLX format from [CohereForAI/aya-23-8B](https://huggingface.co/CohereForAI/aya-23-8B) using mlx-lm version **0.13.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/aya-23-8B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```