# CT-LLM-SFT-experiment-ckpts

[**🌐 Homepage**](https://chinese-tiny-llm.github.io) | [**🤗 MAP-CC**](https://huggingface.co/datasets/m-a-p/MAP-CC) | [**🤗 CHC-Bench**](https://huggingface.co/datasets/m-a-p/CHC-Bench) | [**🤗 CT-LLM**](https://huggingface.co/collections/m-a-p/chinese-tiny-llm-660d0133dff6856f94ce0fc6) | [**📖 arXiv**](https://arxiv.org/abs/2404.04167) | [**GitHub**](https://github.com/Chinese-Tiny-LLM/Chinese-Tiny-LLM)

This warehouse contains all SFT experiment ckpts, which are fine-tuned by different Chinese and English data ratios, as follows:
- zh_105k_en_105k(1:1)
- zh_105k_en_52k(2:1)
- zh_105k_en_26k(4:1)
- zh_105k_en_13k(8:1)
- zh_105k(only Chinese)
- en_105k(only English)

## Uses

Please refer to the usage [CT-LLM-SFT](https://huggingface.co/m-a-p/CT-LLM-SFT)