Top k (LLM Attribute): Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
Maxim@tygron.com (talk | contribs)
Created page with "{{LLM attributes | <onlyinclude> {{LLM attributes|type=row|attribute=TOP_K|unit=number|defaultvalue=64|description=Top-P sampling is an adaptive version of Top L (LLM Attribute). Instead of fixed number of tokens, it cuts off based on cumulative probability.}} </onlyinclude> }} {{article end |notes= |seealso= * Chat Channel#Attributes |api= *Api session items chatchannels *Api session event editor chatchannel set attribute }}"
 
Maxim@tygron.com (talk | contribs)
No edit summary
 
(4 intermediate revisions by the same user not shown)
Line 1: Line 1:
{{LLM attributes
{{LLM attributes
| <onlyinclude>
| <onlyinclude>
{{LLM attributes|type=row|attribute=TOP_K|unit=number|defaultvalue=64|description=Top-P sampling is an adaptive version of [[Top L (LLM Attribute)]]. Instead of fixed number of tokens, it cuts off based on cumulative probability.}} </onlyinclude>
{{LLM attributes|type=row|attribute=TOP_K|unit=number|defaultvalue=64|description=Top-K sampling limits the [[Large Language Model (LLM)|LLM]] model to choosing from the K most likely tokens at each step.}} </onlyinclude>
}}
}}
{{article end
{{article end

Latest revision as of 12:52, 1 July 2026