README.md

metadata

language:
  - en
license: other
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/CodeQwen1.5-7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
  - pretrained
  - mlx

ipetrukha/CodeQwen1.5-7B-4bit

The Model ipetrukha/CodeQwen1.5-7B-4bit was converted to MLX format from Qwen/CodeQwen1.5-7B using mlx-lm version 0.16.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ipetrukha/CodeQwen1.5-7B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)