kernelpool/Hy3-8bit

This model kernelpool/Hy3-8bit was converted to MLX format from tencent/Hy3 using mlx-lm version 0.31.3.

Use with mlx

This model requires Hy3 support from mlx-lm PR #1211, which has not yet been merged. Until it is included in an mlx-lm release, install mlx-lm from the PR branch:

pip install git+https://github.com/ml-explore/mlx-lm.git@refs/pull/1211/head

from mlx_lm import load, generate

model, tokenizer = load("kernelpool/Hy3-8bit")

prompt = "hello"

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

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