aneet-javis

Results 7 comments of aneet-javis

llava_v1_5_mix665k dataset

@taltlusty Where did you get this dataset from? Didn't find in playground/data.

Suspected memory leak during zero3 training. oom eventually after several checkpoint

@leiwen83 @lw3259111 Could you figure out how to solve this? I came across with the same issue.

[Question] Trying to finetune LLAVA on a custom dataset without the use of a GPU.

@tosiyuki Could you please tell what is the format of LLaVA dataset? I'm trying to create a custom dataset for fine-tuning.

[Question] Overfitting in my finetune experiment using my custom data

Could anyone tell what hardware are you guys finetuning on? I tried on one A10G with batch_per_device =1, But getting OOM error.

[Question] no mm_projector.bin after finetune.sh

@gd2016229035 did you figure this out?

[Question] problem porting to other LLM

@zjh908491372 Could you share what all changes are to be made to change the llm in LLaVA? Thanks,

[Question] lora finetune loss=0.00

@Sarahtorekryo I'm also trying to fine-tune LLaVA on custom dataset. Could you share dataset format/resources or code to start with? Thanks.