---
base_model: Nexusflow/Athene-V2-Chat
language:
- en
library_name: transformers
license: other
tags:
- RLHF
- Nexusflow
- Athene
- Chat Model
- mlx
---

# cotdp/Athene-V2-Chat-MLX-4bit

The Model [cotdp/Athene-V2-Chat-MLX-4bit](https://huggingface.co/cotdp/Athene-V2-Chat-MLX-4bit) was converted to MLX format from [Nexusflow/Athene-V2-Chat](https://huggingface.co/Nexusflow/Athene-V2-Chat) using mlx-lm version **0.19.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cotdp/Athene-V2-Chat-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)
```