---
language: en
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
base_model:
- flwrlabs/Lizzy-7B
---
# Lizzy-7B-8bits-mlx

## Introduce

Quant by mlx-lm 0.31.3 with new pipeline for lizzy model_type

[ref](https://github.com/AlphaKure/mlx-lm/tree/lizzy)

## Usage
```
mlx_lm.generate mlx_lm.generate --model /path/to/model --prompt "What is different between CPU and GPU?" --max-tokens 2048 --trust-remote-code
# or
mlx_lm.chat --model /path/to/model --max-tokens 2048 --trust-remote-code
```