---
license: llama2
language:
- ja
- en
base_model: tokyotech-llm/Swallow-70b-instruct-hf
pipeline_tag: text-generation
---

**[2.2bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/4.0bpw)**  (high quality loss, only for 24GB vRAM test.)  
**[4.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/4.0bpw)**  
**[6.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/6.0bpw)**  
**[8.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/8.0bpw)**

# Swallow-70b-instruct-exl2
- Model creator: [tokyotech-llm](https://huggingface.co/tokyotech-llm)
- Original model: [Swallow-70b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf)

## Prompt template

```
### 指示:
{instruction}

### 入力:
{input}

### 応答:

```

### Licence

Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.