QwQ-0.5B-fp16/README.md

datasets, base_model, tags, library_name, pipeline_tag

datasets	base_model	tags	library_name	pipeline_tag
open-r1/OpenR1-Math-220k	InfiniAILab/QwQ-0.5B	mlx	mlx	text-generation

mlx-community/QwQ-0.5B-fp16

This model mlx-community/QwQ-0.5B-fp16 was converted to MLX format from InfiniAILab/QwQ-0.5B using mlx-lm version 0.22.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/QwQ-0.5B-fp16")

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)