README.md

---
base_model: rinna/llama-3-youko-8b-instruct
datasets:
- CohereForAI/aya_dataset
- kunishou/databricks-dolly-15k-ja
- kunishou/HelpSteer-35k-ja
- kunishou/HelpSteer2-20k-ja
- kunishou/hh-rlhf-49k-ja
- kunishou/oasst1-chat-44k-ja
- kunishou/oasst2-chat-68k-ja
- meta-math/MetaMathQA
- OpenAssistant/oasst1
- OpenAssistant/oasst2
- sahil2801/CodeAlpaca-20k
language:
- ja
- en
license: llama3
tags:
- llama
- llama-3
- mlx
thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
inference: false
base_model_relation: merge
---

# mlx-community/rinna-llama-3-youko-8b-instruct-4bit

The Model [mlx-community/rinna-llama-3-youko-8b-instruct-4bit](https://huggingface.co/mlx-community/rinna-llama-3-youko-8b-instruct-4bit) was converted to MLX format from [rinna/llama-3-youko-8b-instruct](https://huggingface.co/rinna/llama-3-youko-8b-instruct) using mlx-lm version **0.19.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/rinna-llama-3-youko-8b-instruct-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)
```