| license: apache-2.0 | |
| base_model: GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0 | |
| tags: | |
| - mlx | |
| # GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx | |
| This quantized low-bit model [GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx) was converted to MLX format from [`GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0`](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0) using gbx-lm version **0.3.5**. | |
| Refer to the [original model card](https://huggingface.co/GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0) for more details on the model. | |
| ## Use with mlx | |
| ```bash | |
| pip install gbx-lm | |
| ``` | |
| ```python | |
| from gbx_lm import load, generate | |
| model, tokenizer = load("GreenBitAI/DeepSeek-R1-Distill-Qwen-14B-layer-mix-bpw-4.0-mlx") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |