How to do batch inference using this SmolVLM-Instruct ?
#19
by
dutta18
- opened
I have a VQA dataset. I wanted to do batch inference to see the performance of this model.
How do I organize the chat template ?
Is it something like below?
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "what is the color of the sky"}
]
},
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "what is the color of the grass"}
]
},
]