Qwen2.5-14B-8bit / README.md
prince-canuma's picture
Upload folder using huggingface_hub (#1)
1285553 verified
metadata
language:
  - en
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-14B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
  - mlx

mlx-community/Qwen2.5-14B-8bit

The Model mlx-community/Qwen2.5-14B-8bit was converted to MLX format from Qwen/Qwen2.5-14B 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/Qwen2.5-14B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)