27 lines
556 B
Markdown
27 lines
556 B
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- pretrained
|
||
|
|
- mlx
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# mlx-community/Qwen2-0.5B
|
||
|
|
|
||
|
|
The Model [mlx-community/Qwen2-0.5B](https://huggingface.co/mlx-community/Qwen2-0.5B) was converted to MLX format from [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) using mlx-lm version **0.14.0**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("mlx-community/Qwen2-0.5B")
|
||
|
|
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
||
|
|
```
|