Crossing Linguistic Horizons

Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Weak-Prompt Question Answering Leaderboard

Models XQuAD MLQA
EM F1 EM F1
URA-LLaMa 70B 0.21 ± 0.01 0.47 ± 0.01 0.14 ± 0.01 0.41 ± 0.00
URA-LLaMa 13B 0.22 ± 0.01 0.43 ± 0.01 0.17 ± 0.01 0.40 ± 0.01
URA-LLaMa 7B 0.13 ± 0.00 0.32 ± 0.00 0.10 ± 0.00 0.32 ± 0.00
LLaMa-2 13B 0.04 ± 0.00 0.28 ± 0.00 0.04 ± 0.00 0.28 ± 0.00
LLaMa-2 7B 0.06 ± 0.00 0.24 ± 0.00 0.05 ± 0.00 0.24 ± 0.00
MixSUra 8x7b 0.13 ±- 0.38 ± - 0.09 ± - 0.36 ± -