prince-canuma's picture
2338714d62982c0dd49553b389c7335a78dde65eba0377608792457aa1d07839
a6c60f2 verified
|
raw
history blame
756 Bytes
metadata
language:
  - en
license: other
tags:
  - chat
  - mlx
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen2-Math-72B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation

mlx-community/Qwen2-Math-72B-Instruct-bf16

The Model mlx-community/Qwen2-Math-72B-Instruct-bf16 was converted to MLX format from Qwen/Qwen2-Math-72B-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-72B-Instruct-bf16")
response = generate(model, tokenizer, prompt="hello", verbose=True)