danchev/ granite-docling:latest

539 4 months ago

Granite Docling is a multimodal Image-Text-to-Text model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

vision 258m
... /
template
f2f8764b76f7 · 236B
{{- range $message := .Messages -}}
{{- "<|start_of_role|>" }}{{ $message.Role }}{{ "<|end_of_role|>" -}}
{{- $message.Content -}}
{{- "<|end_of_text|>\n" -}}
{{- end -}}
{{- "<|start_of_role|>assistant<|end_of_role|>" -}}