splunk/DECEIVE
1
0
Fork 0
mirror of https://github.com/splunk/DECEIVE.git synced 2025-07-02 00:57:26 -04:00
Code Issues Packages Projects Releases Wiki Activity

Added 'temperature' parameter to control randomness in LLM responses.

Browse Source 
Lower temps mean less randomness in the  responses, which increase the chances of consistency between sessions. Not a guarantee, though.
This commit is contained in:
David J. Bianco
2025-04-25 09:12:40 -04:00
parent a3c14bbf15
commit 10e2f11599
2 changed files with 23 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
SSH/config.ini.TEMPLATE
View File

@ -53,6 +53,12 @@ model_name = gpt-4o
#llm_provider = gemini
#model_name = gemini-1.5-pro
# Temperature controls randomness in LLM responses. Values usually range from 0.0 to 2.0.
# Lower values (e.g., 0.2) make responses more focused and deterministic.
# Higher values (e.g., 0.8) make responses more creative and variable.
# Default is 0.2.
temperature = 0.2
# The maximum number of tokens to send to the LLM backend in a single
# request. This includes the message history for the session, so should
# be fairly high. Not all models support large token counts, so be sure