| pipeline_tag: text-generation | |
| library_name: transformers | |
| language: | |
| - en | |
| thumbnail: '"https://cdn-uploads.huggingface.co/production/uploads/62f93f9477b722f1866398c2/69escIKmO-vEzFUj_m0WX.png"' | |
| tags: | |
| - text-generation | |
| - uncensored | |
| - direct-answer | |
| - information-retrieval | |
| - general-knowledge | |
| - unfiltered | |
| - amoral-ai | |
| - mlx | |
| - mlx-my-repo | |
| base_model: soob3123/GrayLine-Gemma3-4B | |
| datasets: | |
| - soob3123/GrayLine-QA | |
| license: apache-2.0 | |
| # Disya/GrayLine-Gemma3-4B-mlx-4Bit | |
| The Model [Disya/GrayLine-Gemma3-4B-mlx-4Bit](https://huggingface.co/Disya/GrayLine-Gemma3-4B-mlx-4Bit) was converted to MLX format from [soob3123/GrayLine-Gemma3-4B](https://huggingface.co/soob3123/GrayLine-Gemma3-4B) using mlx-lm version **0.28.3**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("Disya/GrayLine-Gemma3-4B-mlx-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) | |
| ``` | |