Dau Thi Van Anh comments

Repositories
Issues
Comments

Results 2 comments of


                                            Dau Thi Van Anh

FSDP Must flatten tensors with uniform dtype but got torch.bfloat16 and torch.float32

> as was said above, remove `prepare_model_for_kbit_training` > > this solved the issue for me > > https://github.com/huggingface/peft/blob/main/src/peft/utils/other.py#L128 Hi. Thank you for your solution, but I don't get it. Should...

Evaluations and Prompts

Hi @prince14322. Thank you for your attention. Prompts are included in [MainframeBench](https://huggingface.co/datasets/Fsoft-AIC/MainframeBench). We call 3 times for each model and get an average for the result. Regarding evaluation scripts, we...