---
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model: webAI-Official/TwIL-LM3
license: other
license_name: webai-non-commercial-license-ver.-1.0
license_link: https://huggingface.co/webAI-Official/webAI-ColVec1-4b/blob/main/LICENSE.md
tags:
- formal-logic
- reasoning
- lora
- model-merging
- wise-ft
- reinforcement-learning
- grpo
- smollm3
- twil-lm
- mlx
- mlx-my-repo
---

# usermma/TwIL-LM3-mlx-fp16

The Model [usermma/TwIL-LM3-mlx-fp16](https://huggingface.co/usermma/TwIL-LM3-mlx-fp16) was converted to MLX format from [webAI-Official/TwIL-LM3](https://huggingface.co/webAI-Official/TwIL-LM3) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("usermma/TwIL-LM3-mlx-fp16")

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)
```