theignorantt comments

Repositories
Issues
Comments

Results 3 comments of


                                            theignorantt

Meet problem when reproduce the performance reported in the paper.

> Hi @siyueyu I faced a similar problem, where the performance just around 55-57 mIoU. Have you figured out the issue yet. Thanks the same problem. Have you figured out...

Meet problem when reproduce the performance reported in the paper.

> Thanks for addressing the problem! We will update the training config with EMA (as we did). looking forward to your update! I tried to modify several places, such as...

[Bug] LoRA finetune doesnt generate any output text

> I experienced the same issue finetuning the 40B variant - loading the resulting model would produce no outputs. > > I had to run `python tools/merge_lora.py` on the finetuned...