| license: apache-2.0 | |
| license_link: https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE | |
| language: | |
| - en | |
| pipeline_tag: text-generation | |
| base_model: Qwen/QwQ-32B-Preview | |
| tags: | |
| - chat | |
| - mlx | |
| library_name: transformers | |
| # abalogh/QwQ-32B-Preview-4bit | |
| The Model [abalogh/QwQ-32B-Preview-4bit](https://huggingface.co/abalogh/QwQ-32B-Preview-4bit) was | |
| converted to MLX format from [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) | |
| using mlx-lm version **0.20.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("abalogh/QwQ-32B-Preview-4bit") | |
| prompt="hello" | |
| if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: | |
| messages = [{"role": "user", "content": prompt}] | |
| prompt = tokenizer.apply_chat_template( | |
| messages, tokenize=False, add_generation_prompt=True | |
| ) | |
| response = generate(model, tokenizer, prompt=prompt, verbose=True) | |
| ``` | |