Zhang

Results 8 comments of Zhang

Custom training in Colab version, stuck on error --> LightningDistributedDataParallel' object has no attribute '_sync_params'

hi smithee77, have you solved this problem?

How to use the sliding attention window mechanism？

hi What operating system do you run the code on? windows or linux. I ran the code on winodws system but i encountered bugs that i cant fix

[Usage] After fine-tuning LLaVA 1.5, mm_projector.bin file is not available

> > Add 'lora' in the folder name helped mine. Merged model could run inference and showed the affection of fine-tuning. I assume you can run inference without merging if...

AttributeError: module 'signal' has no attribute 'SIGUSR1'

hi have you solve this problem？

[Question] Finetuning bash file

Have you figured it out? I attempted to apply the llavaplus application to my task, but the memory usage was too high.

[Question] Finetuning bash file

Thank you for your reply! @AlirezaShamsoshoara Did you get good results just by changing the `projector_type` and `vision_tower` and using the `training_llava_plus_v0_7b.sh` script with `zero2.json`? I created a test dataset...

[Question] Finetuning bash file

I can't use `zero3.json` to fine-tune the model with LoRA, so i finetune the model with `zero2.json`. But when I use the model fine-tuned with `zero2.json`, it gives the following...

[Question] No scheme supplied

same problem. have you guys fix it?