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](https://github.com/Facico/Chinese-Vicuna) work. | |
Specially, this is the 4bit version trained with qlora |