bytedance/dolphin

Document Image Parsing via Heterogeneous Anchor Prompting

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`file`*	string(uri)	PDF or image file to parse	`—`	—
`output_format`	string	Output format	`"markdown_content"`	markdown_contentjson_content

filerequiredstring

PDF or image file to parse

output_formatstring

Output format

Default: "markdown_content"

markdown_contentjson_content

Version: 3076d1f489b2Updated: 7/25/20261.3K runs