search

RUCAIBox / LLMBox

A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.
MIT License
578 stars 74 forks source link

Add MGSM dataset #223

Closed HMWABY closed 4 months ago

HMWABY commented 4 months ago

Finished the following tests:

python inference.py -m gpt-3.5-turbo -d mgsm:en --evaluation_set test\[:20\] -b 20
python inference.py -m gpt-3.5-turbo -d mgsm:en --evaluation_set test\[:20\] -b 20 -shots 8
python inference.py -m gpt-3.5-turbo -d mgsm:en --evaluation_set test\[:20\] -b 20 -shots 8 --cot least_to_most
python inference.py -m gpt-3.5-turbo -d mgsm:en --evaluation_set test\[:20\] -b 20 -shots 8 --cot pal