metadata
base_model: unsloth/QwQ-32B
license: apache-2.0
license_link: https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
- qwen
- mlx
bobig/QwQ-32B-4.5bit
The Model bobig/QwQ-32B-4.5bit was converted to MLX format from unsloth/QwQ-32B using mlx-lm version 0.21.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("bobig/QwQ-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)