Hi. I’m working on fine-tuning seq2seq models and having a question about the validation of the generated output. As far as I understand, when using beam search for text generation, it is possible to get a sequences_scores metric from the generate() function as described here . Is it right that this…

Text generation confidence

Yevgen December 7, 2022, 3:43pm 2

Hi, did you ever find a solution to your question?

Topic		Replies	Views
How to get the scores of a certain beam 🤗Transformers	0	379	June 13, 2022
Generation Probabilities: How to compute probabilities of output scores for GPT2 🤗Transformers	24	28884	April 5, 2023
Text generation pipeline - output_scores parameter Models	1	3963	January 20, 2021
Trocr Inference confidence problem Models	0	262	March 1, 2024
Does the GPT-2 model have a confidence score for text generation result? Beginners	1	1167	May 24, 2023