Output is truncated in inference API
#15
by joekr552 - opened
For many chain of thought examples, the models output seem overly truncated. and the max_length don't seem respected.
Bug?
Eg. try this input
'Answer the following question by reasoning step by step. The cafeteria had 23 apples. If they used 20 for lunch, and bought 6 more, then they gave away 2, how many apple do they have?"