Property VlmMaximumCompletionTokens
- Namespace
- LMKit.Document.Conversion
- Assembly
- LM-Kit.NET.dll
VlmMaximumCompletionTokens
Gets or sets the maximum number of completion tokens emitted by the vision model
per page. Use -1 to disable the limit. Defaults to 3072.
public int VlmMaximumCompletionTokens { get; set; }
Property Value
Examples
// No cap: let the VLM emit as many tokens as the page needs.
var options = new DocumentToMarkdownOptions { VlmMaximumCompletionTokens = -1 };
Remarks
Raise this when pages are dense enough to truncate mid-sentence (set GeneratedTokenCount against this value to detect the case). Lowering the cap speeds up conversion at the risk of missing tail content on long pages.