RioShiina's picture
Update README.md
fdcf3fc verified
---
license: llama2
language:
- ja
- en
base_model: tokyotech-llm/Swallow-70b-NVE-instruct-hf
pipeline_tag: text-generation
---
**[2.2bpw](https://huggingface.co/rioshiina/Swallow-70b-NVE-instruct-exl2/tree/2.2bpw)** (high quality loss, only for 24GB vRAM test.)
**[4.0bpw](https://huggingface.co/rioshiina/Swallow-70b-NVE-instruct-exl2/tree/4.0bpw)**
**[6.0bpw](https://huggingface.co/rioshiina/Swallow-70b-NVE-instruct-exl2/tree/6.0bpw)**
**[8.0bpw](https://huggingface.co/rioshiina/Swallow-70b-NVE-instruct-exl2/tree/8.0bpw)**
# Swallow-70b-NVE-instruct-exl2
- Model creator: [tokyotech-llm](https://huggingface.co/tokyotech-llm)
- Original model: [Swallow-70b-NVE-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-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.