Model is not inferencing on multiple images; is this the right template?
#4
by
ltbd78
- opened
conversation = [
{
"role": "User",
"content": "Compare and contrast <image_placeholder> and <image_placeholder>.",
"images": ["./data/1.png", "./data/2.jpg"]
},
{
"role": "Assistant",
"content": ""
}
]
UPDATE: it worked for a different set of images and prompt "Describe <image_placeholder>. Then describe <image_placeholder>."
Though, I would like to clarify: how is order determined? Is it sequential?
Yes, for the multi-image inputs, your prompt is correct. Additionally, these images are sequential. The first <image_placeholder> corresponds to "./data/1.png," while the second <image_placeholder> corresponds to "./data/2.png."
This comment has been hidden
@doubility123 For me, multi image input does not work at all. Was deepseek VL trained on multi image-text pairs?
For our model, we need to train on multi image-text pairs, does the architecture support that?
Thanks