Seulbi Lee
Seulbi Lee
**Describe the bug** Hello, I am training VAE. The resolution of the data is large, so I've been using deepspeed recently. However, with deepspeed, all iteration of the first epoch...
Hi! First of all, thank you so much for sharing such an easy-to-use tool, I did from pretraining to finetuning thanks to you. I just wanted to ask, how do...
Hi, I'm going to train the LLaVA-NeXT (image ver.) myself before fine-tuning. The authors provide a script for pre-training named "./scripts/train/pretrain_clip.sh" as follows. ``` export OMP_NUM_THREADS=8 export NCCL_IB_DISABLE=0 export NCCL_IB_GID_INDEX=3...
Thanks for your great work. I would like to train the model with Gemma2 or Phi4, as you have done with your paper. However, I couldn't find the version (conversation)...