README.md

metadata

license: other
license_name: qwen-research
license_link: >-
  https://raw.githubusercontent.com/QwenLM/Qwen/refs/heads/main/Tongyi%20Qianwen%20RESEARCH%20LICENSE%20AGREEMENT
base_model: ozone-research/Chirp-01
tags:
  - mlx

alexgusevski/Chirp-3B-q8-mlx

The Model alexgusevski/Chirp-3B-q8-mlx was converted to MLX format from ozone-research/Chirp-01 using mlx-lm version 0.21.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Chirp-3B-q8-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)