Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-6Bit

1---2base_model: Novaciano/SEX_ROLEPLAY-3.2-1B3library_name: transformers4tags:5- mergekit6- merge7- rp8- roleplay9- gguf10- 1b11- 4-bit12- nsfw13- uncensored14- sillytavern15- koboldcpp16- not-for-all-audiences17- mlx18- mlx-my-repo19language:20- es21- en22pipeline_tag: text-generation23license: apache-2.024---25 26# Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-6Bit27 28The Model [Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-6Bit](https://huggingface.co/Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-6Bit) was converted to MLX format from [Novaciano/SEX_ROLEPLAY-3.2-1B](https://huggingface.co/Novaciano/SEX_ROLEPLAY-3.2-1B) using mlx-lm version **0.22.1**.29 30## Use with mlx31 32```bash33pip install mlx-lm34```35 36```python37from mlx_lm import load, generate38 39model, tokenizer = load("Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-6Bit")40 41prompt="hello"42 43if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:44    messages = [{"role": "user", "content": prompt}]45    prompt = tokenizer.apply_chat_template(46        messages, tokenize=False, add_generation_prompt=True47    )48 49response = generate(model, tokenizer, prompt=prompt, verbose=True)50```51