from mlx_lm import load, generate

model, tokenizer = load("bobig/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit")

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)

mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit

bobig/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit

Use with mlx

mlx-community/
FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit