156 1 week ago

Chandra-OCR-2 from Datalab is a state-of-the-art OCR model that outputs structured markdown, HTML, or JSON while preserving precise layout information from images and PDFs across 90+ languages. there is another of this in Ollama but unpatched [no vision?]

vision tools thinking
63ca5dffc26b · 195B
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
/nothink {{ .Prompt }}<|im_end|>
<|im_start|>assistant
<think>
</think>
{{ .Response }}<|im_end|>