It feels like the model has overfitted the training dataset...
#2
by SelimAI - opened
Hello,
I'm very interested in your work about SVGs and how you can improve the output provided by LLMs. However, I've encountered significant brittleness when testing OmniSVG1.1_8B, even with recommended prompts.
For example, here is a recommended prompt that works as expected :
but here is the same prompt, only for a different color :
same thing here, the adherence to the prompt isn't great either :
Here is another recommended prompt :
but changing colour once again gives some unexpected result.
For information, I'm using OmniSVG1.1_8B on default settings.
Am I doing something wrong here ?
Thanks in advance.