qwen2.5-0.5b-support-assistant

arinltte/qwen2.5-0.5b-support-assistant

This model arinltte/qwen2.5-0.5b-support-assistant was converted to MLX format from Qwen/Qwen2.5-0.5B-Instruct using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("arinltte/qwen2.5-0.5b-support-assistant")

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)

Usage

Live demo: huggingface.co/arinltte/support-assistant-demo