metadata
base_model: Qwen/Qwen2.5-Math-72B
language:
- en
library_name: transformers
license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
- mlx
mlx-community/Qwen2.5-Math-72B-Instruct-8bit
The Model mlx-community/Qwen2.5-Math-72B-Instruct-8bit was converted to MLX format from Qwen/Qwen2.5-Math-72B-Instruct using mlx-lm version 0.18.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen2.5-Math-72B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)