Failed to create new sequence: failed to process inputs: this model is missing data required for image input
my modelfile ,

Modelfile for amoral-gemma3-12B-v2-qat-Q4_0-GGUF (Multimodal Vision Model)

Download the model file first from: https://huggingface.co/soob3123/amoral-gemma3-12B-v2-qat-Q4_0-GGUF

FROM ./amoral-gemma3-12b-v2-qat-q4_0.gguf

Multimodal vision template for Gemma format

TEMPLATE """user
{{ if .Images }}{{ range .Images }}{{ . }}{{ end }}{{ end }}{{ .Prompt }}
model
{{ .Response }}
"""

Vision-optimized parameters

PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER repeat_penalty 1.1
PARAMETER num_ctx 8192
PARAMETER num_predict -1
PARAMETER stop ""
PARAMETER stop ""

Vision-specific parameters

PARAMETER num_thread 8
PARAMETER num_gpu 1
PARAMETER use_mmap true
PARAMETER use_mlock false

System message for multimodal capabilities

SYSTEM """You are a multimodal AI assistant capable of understanding and analyzing both text and images. You can describe images, answer questions about visual content, read text in images, and engage in conversations that combine visual and textual information."""