Search Results for author:
Found 1 papers, 1 papers with code
Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity
Experiments show that for low values of k and p in top-k and top-p sampling, perplexity drops significantly with generated text length, which is also correlated with excessive repetitions in the text (the boredom trap).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
