|
|
--- |
|
|
license: mit |
|
|
library_name: mlx |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- transformers |
|
|
- mlx |
|
|
base_model: |
|
|
- XiaomiMiMo/MiMo-V2-Flash |
|
|
--- |
|
|
|
|
|
# mlx-community/MiMo-V2-Flash-mlx-8bit |
|
|
|
|
|
This model [mlx-community/MiMo-V2-Flash-mlx-8bit-](https://huggingface.co/mlx-community/MiMo-V2-Flash-mlx-8bit) was converted to MLX format from [XiaomiMiMo/MiMo-V2-Flash](https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash) |
|
|
using mlx-lm version **0.30.0**. |
|
|
|
|
|
You can find more similar MLX model quants for a single Apple Mac Studio M3 Ultra with 512 GB at https://huggingface.co/bibproj |
|
|
|
|
|
--- |
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("mlx-community/MiMo-V2-Flash-mlx-8bit") |
|
|
|
|
|
prompt = "hello" |
|
|
|
|
|
if tokenizer.chat_template is not None: |
|
|
messages = [{"role": "user", "content": prompt}] |
|
|
prompt = tokenizer.apply_chat_template( |
|
|
messages, add_generation_prompt=True |
|
|
) |
|
|
|
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True) |
|
|
``` |
|
|
|
