Maximum number of tokens to generate. A word is generally 2-3 tokens Default value: 512

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value. Default value: 0.75

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens Default value: 1

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens. Defaults to 0 (no top-k sampling). 0

When > 0 and top_k > 1, penalizes new tokens based on their similarity to previous tokens. Can help minimize repitition while maintaining semantic coherence. Set to 0 to disable. 0

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it. Default value: 1

Increasing the length_penalty parameter above 1.0 will cause the model to favor longer sequences, while decreasing it below 1.0 will cause the model to favor shorter sequences. Default value: 1

If set to int > 0, all ngrams of size no_repeat_ngram_size can only occur once. 0

Set seed for reproducible outputs. Set to -1 for random seed. Default value: -1