eternis/eternis_anonymizer_qwen_0.6b_mlx_20Sep

This model eternis/eternis_anonymizer_qwen_0.6b_mlx_20Sep was converted to MLX format from eternis/eternis_sft_tool_calling_Qwen0.6B_27jul_merged_llamacpp using mlx-lm version 0.28.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("eternis/eternis_anonymizer_qwen_0.6b_mlx_20Sep")

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)