Captured photo
GPT-OSS 120B
30

About

120b open-weight language model from OpenAI

Percs

High creativity in output
Exceptional accuracy
Fast processing speed
Versatile functionality
Enhanced efficiency
Open-weight model

Settings

Max Tokens-  The maximum number of tokens the model should generate as output.
Temperature-  The value used to modulate the next token probabilities.
Presence Penalty-  Presence penalty
Frequency Penalty-  Frequency penalty
Top P-  Top-p (nucleus) sampling
Context Capacity-  undefined