GitLab

Implement SQuADv2 evaluation

# Conflicts:
#	lm_eval/tasks/squad.py

Add `Random` argument to `write_out` `fewshot_context`

Remove unused imports and format imports

Adding hendrycksTest (https://arxiv.org/abs/2009.03300)

Added MATH dataset

Drawing fewshot from train_docs has two main advantages: a) you can do way more than 8 shots and b) your fewshot examples are from the same type of problem