metadata
language:
- en
license: apache-2.0
tags:
- chat
- mlx
pipeline_tag: text-generation
mlx-community/Qwen2-Math-7B-Instruct-4bit
The Model mlx-community/Qwen2-Math-7B-Instruct-4bit was converted to MLX format from Qwen/Qwen2-Math-7B-Instruct using mlx-lm version 0.16.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen2-Math-7B-Instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)