You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have a custom dataset that I want to finetune LLaVA on. I was wondering is this the format my dataset should have for finetuning LLaVA? and if so, how the answer for "value" for "gpt" should be provided if these values are LLaVA generated answers? or these are ground-truth answers?
[
{
"id": "997bb945-628d-4724-b370-b84de974a19f",
"image": "part-000001/997bb945-628d-4724-b370-b84de974a19f.jpg",
"conversations": [
{
"from": "human",
"value": "<image>\nWrite a prompt for Stable Diffusion to generate this image."
},
{
"from": "gpt",
"value": "a beautiful painting of chernobyl by nekro, pascal blanche, john harris, greg rutkowski, sin jong hun, moebius, simon stalenhag. in style of cg art. ray tracing. cel shading. hyper detailed. realistic. ue 5. maya. octane render. "
},
]
},
...
]
The text was updated successfully, but these errors were encountered:
Question
I have a custom dataset that I want to finetune LLaVA on. I was wondering is this the format my dataset should have for finetuning LLaVA? and if so, how the answer for "value" for "gpt" should be provided if these values are LLaVA generated answers? or these are ground-truth answers?
The text was updated successfully, but these errors were encountered: