EvalSetup¶ code_chat¶ mbpp_chat code_generation¶ jhumaneval jhumaneval_tab_indent mbpp mbpp_tab_indent openai_humaneval openai_humaneval_tab_indent en_chat¶ mt-en vicuna-en en_generation¶ babi commonsense_qa gsm8k squad_v1 trivia_qa twitter_sentiment en_multiple_choice¶ arc_challenge arc_easy commonsense_qa_mc hellaswag openbookqa piqa xwinograd_en en_perplexity¶ tiny_shakespeare ja_chat¶ aio_chat elyza_tasks_100 mgsm_ja_chat mt-ja rakuda-v2-ja vicuna-ja ja_generation¶ aio jcommonsenseqa jnli jsquad mgsm_ja wrime_pos_neg xlsum_ja ja_multiple_choice¶ jcommonsenseqa_mc xwinograd_ja translation¶ wmt20_en_ja wmt20_ja_en translation_chat¶ wmt20_en_ja_chat wmt20_ja_en_chat