metadata
license: gpl-3.0
datasets:
- BelleGroup/generated_train_0.5M_CN
- JosephusCheung/GuanacoDataset
- Chinese-Vicuna/guanaco_belle_merge_v1.0
language:
- zh
tags:
- alpaca
- Chinese-Vicuna
- llama
This is a Chinese instruction-tuning lora checkpoint based on llama-7B(1epoch) from this repo's work. Specially, this is the 4bit version trained with qlora