GitHub - danesherbs/self-taught-critiquer: Reducing the time to create critique-writing models by 100-1000x on n-digit arithmetic problems by getting the model to learn from its own generated outputs.

News: this won best poster at the Safe and Trustworthy AI Workshop 2022!

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
notebooks		notebooks
scripts		scripts
README.md		README.md
critique_arithmetic.py		critique_arithmetic.py
critique_arithmetic_sweep.py		critique_arithmetic_sweep.py
datasets.py		datasets.py
requirements.txt		requirements.txt
stac.py		stac.py
stac_discriminator_sweep.py		stac_discriminator_sweep.py
stac_sweep.py		stac_sweep.py
test_datasets.py		test_datasets.py
test_utils.py		test_utils.py
utils.py		utils.py

Provide feedback