|
|
|
|
|
|
by gliptic
785 days ago
|
|
|
Incorrect. The output of the decoder LLM is logits that are then divided by the temperature and passed through softmax to give the probabilities. You can't actually set temperature to 0 (division by zero), but in the limit where temperature approaches 0, softmax converges to argmax. Temperature = 1 is where it's not pushed in either direction. |
|
|