Jing Zhu comments

Repositories
Issues
Comments

Results 6 comments of


                                            Jing Zhu

RuntimeError: CUDA error: out of memory for "DRN-D-105" while testing

same issue

Error when running TransE

I met the exact same problem if I train TransE using KvsAll type. But training it with NegativeSampling will solve the problem. Any insight on this?

Error when running TransE

Nope. I updated to 1.9.0 and the same problem exists. That's weird.

Error when running TransE

Thanks for reopening the issue :). It's great help for our research!

Do the published training weights "7b_tiva_v0" include all three stages of training results simultaneously?

Is there any suggestions on how to load 7b_tiva_v0 during training stage? I tried to continue instruction training on my own data starting from the provided 7b_tiva_v0 checkpoints. However, simply...

How to create T2M data?

same question here