| license: apache-2.0 | |
| license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-32B/blob/main/LICENSE | |
| language: | |
| - en | |
| base_model: Qwen/Qwen2.5-Coder-32B | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| tags: | |
| - code | |
| - qwen | |
| - qwen-coder | |
| - codeqwen | |
| - mlx | |
| - mlx-my-repo | |
| # Scotto2025/Qwen2.5-Coder-32B-mlx-8Bit | |
| The Model [Scotto2025/Qwen2.5-Coder-32B-mlx-8Bit](https://huggingface.co/Scotto2025/Qwen2.5-Coder-32B-mlx-8Bit) was converted to MLX format from [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B) using mlx-lm version **0.22.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("Scotto2025/Qwen2.5-Coder-32B-mlx-8Bit") | |
| 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) | |
| ``` | |