Fix bug: Prevent inconsistent return value with `eos_early_stop`
#2
by
Lucasoppem
- opened
When eos_early_stop = True, generate() returns prompt + answer;
When eos_early_stop = False, generate() returns answer.
This caused issues during evaluation.
Proposed changes now ensure that the generate() function only returns prompt + answer, consistent with the output of generate() in llada and llada 1.5. (ps: In llada and llada 1.5, generate() returns prompt + answer)