This model was exported using GPTQModel.
How to run this model
# install mlx
pip install mlx_lm
from mlx_lm import load, generate
mlx_path = "ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-mlx-v3"
mlx_model, tokenizer = load(mlx_path)
prompt = "The capital of France is"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
text = generate(mlx_model, tokenizer, prompt=prompt, verbose=True)
Export gptq to mlx
# install gptqmodel with mlx
pip install gptqmodel[mlx] --no-build-isolation
from gptqmodel import GPTQModel
# load gptq quantized model
gptq_model_path = "ModelCloud/QwQ-32B-Preview-gptqmodel-4bit-vortex-v3"
mlx_path = f"./vortex/QwQ-32B-Preview-gptqmodel-4bit-vortex-mlx-v3"
# export to mlx model
GPTQModel.export(gptq_model_path, mlx_path, "mlx")