Top p (LLM Attribute): Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
Maxim@tygron.com (talk | contribs)
No edit summary
Maxim@tygron.com (talk | contribs)
No edit summary
Line 1: Line 1:
{{LLM attributes
{{LLM attributes
| <onlyinclude>
| <onlyinclude>
{{LLM attributes|type=row|attribute=TOP_P|unit=number|defaultvalue=0.95|description=Top-K sampling truncates the probability list before sampling of the [[Large Language Model (LLM)|LLM]].}} </onlyinclude>
{{LLM attributes|type=row|attribute=TOP_P|unit=number|defaultvalue=0.95|description=Top-P selects tokens based on cumulative probability inside the [[Large Language Model (LLM)|LLM]].}} </onlyinclude>
}}
}}
{{article end
{{article end

Revision as of 12:49, 1 July 2026