You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi to all, i'm trying to use example https://ludwig.ai/latest/examples/llms/llm_zero_shot_text_generation/ in python, probably there something i'm missing. But prediction results seems to me to be inconsinstent. Follow the the output.
ZeroShot_Inference_log.log
I think that prediction should be the answer of Q&A but seems to be the tokenised question.
Finished predicting in: 1.42s.
Answer_predictions ... Answer_probability
0 [\n, \n, The, continent, of] ... -inf
1 [\n, \n, The, largest, lake] ... -inf
2 [\n, \n, The, largest, flower] ... -inf
3 [\n, \n, The, diameter, of] ... -inf
Thank you in advance for help.
Beta Was this translation helpful? Give feedback.
All reactions