---
base_model: Novaciano/SEX_ROLEPLAY-3.2-1B
library_name: transformers
tags:
- mergekit
- merge
- rp
- roleplay
- gguf
- 1b
- 4-bit
- nsfw
- uncensored
- sillytavern
- koboldcpp
- not-for-all-audiences
- mlx
- mlx-my-repo
language:
- es
- en
pipeline_tag: text-generation
license: apache-2.0
---

# Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-4Bit

The Model [Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-4Bit](https://huggingface.co/Novaciano/SEX_ROLEPLAY-3.2-1B-mlx-4Bit) 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**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("Novaciano/SEX_ROLEPLAY-3.2-1B-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)
```