---
license:
- llama3.3
- gemma
base_model: tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
base_model_relation: quantized
language:
- en
- ja
---

**[2.2bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/2.2bpw)**  
**[3.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/3.0bpw)**  
**[4.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/4.0bpw)**  
**[5.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/5.0bpw)**  
**[6.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/6.0bpw)**  
**[7.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/7.0bpw)**  
**[8.0bpw](https://huggingface.co/rioshiina/Llama-3.3-Swallow-70B-Instruct-v0.4-exl2/tree/8.0bpw)**

## Calibration Dataset
[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)

## Llama-3.3-Swallow-70B-Instruct-v0.4-exl2
- Model creator: [tokyotech-llm](https://huggingface.co/tokyotech-llm)
- Original model: [Llama-3.3-Swallow-70B-Instruct-v0.4](https://huggingface.co/tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4)

## License
[META LLAMA 3.3 COMMUNITY LICENSE](https://www.llama.com/llama3_3/license/) and [Gemma Terms of Use](https://ai.google.dev/gemma/terms)