| babi_qa:task=15,model=AlephAlpha_luminous-base | generation |
| babi_qa:task=15,model=AlephAlpha_luminous-extended | generation |
| babi_qa:task=15,model=AlephAlpha_luminous-supreme | generation |
| babi_qa:task=15,model=ai21_j1-grande | generation |
| babi_qa:task=15,model=ai21_j1-grande-v2-beta | generation |
| babi_qa:task=15,model=ai21_j1-jumbo | generation |
| babi_qa:task=15,model=ai21_j1-large | generation |
| babi_qa:task=15,model=ai21_j2-grande | generation |
| babi_qa:task=15,model=ai21_j2-jumbo | generation |
| babi_qa:task=15,model=ai21_j2-large | generation |
| babi_qa:task=15,model=anthropic_stanford-online-all-v4-s3 | generation |
| babi_qa:task=15,model=cohere_command-medium-beta | generation |
| babi_qa:task=15,model=cohere_command-xlarge-beta | generation |
| babi_qa:task=15,model=cohere_large-20220720 | generation |
| babi_qa:task=15,model=cohere_medium-20220720 | generation |
| babi_qa:task=15,model=cohere_medium-20221108 | generation |
| babi_qa:task=15,model=cohere_small-20220720 | generation |
| babi_qa:task=15,model=cohere_xlarge-20220609 | generation |
| babi_qa:task=15,model=cohere_xlarge-20221108 | generation |
| babi_qa:task=15,model=microsoft_TNLGv2_530B | generation |
| babi_qa:task=15,model=microsoft_TNLGv2_7B | generation |
| babi_qa:task=15,model=openai_ada | generation |
| babi_qa:task=15,model=openai_babbage | generation |
| babi_qa:task=15,model=openai_code-cushman-001 | generation |
| babi_qa:task=15,model=openai_code-davinci-002 | generation |
| babi_qa:task=15,model=openai_curie | generation |
| babi_qa:task=15,model=openai_davinci | generation |
| babi_qa:task=15,model=openai_gpt-3.5-turbo-0301 | generation |
| babi_qa:task=15,model=openai_text-ada-001 | generation |
| babi_qa:task=15,model=openai_text-babbage-001 | generation |
| babi_qa:task=15,model=openai_text-curie-001 | generation |
| babi_qa:task=15,model=openai_text-davinci-002 | generation |
| babi_qa:task=15,model=openai_text-davinci-003 | generation |
| babi_qa:task=15,model=together_bloom | generation |
| babi_qa:task=15,model=together_glm,stop=hash | generation |
| babi_qa:task=15,model=together_gpt-j-6b | generation |
| babi_qa:task=15,model=together_gpt-neox-20b | generation |
| babi_qa:task=15,model=together_opt-175b | generation |
| babi_qa:task=15,model=together_opt-66b | generation |
| babi_qa:task=15,model=together_redpajama-incite-base-3b-v1 | generation |
| babi_qa:task=15,model=together_t0pp,stop=hash | generation |
| babi_qa:task=15,model=together_t5-11b,stop=hash | generation |
| babi_qa:task=15,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| babi_qa:task=15,model=together_yalm | generation |
| babi_qa:task=15,model=writer_palmyra-instruct-30 | generation |
| babi_qa:task=15,model=writer_palmyra-x | generation |
| babi_qa:task=19,model=AlephAlpha_luminous-base | generation |
| babi_qa:task=19,model=AlephAlpha_luminous-extended | generation |
| babi_qa:task=19,model=AlephAlpha_luminous-supreme | generation |
| babi_qa:task=19,model=ai21_j1-grande | generation |
| babi_qa:task=19,model=ai21_j1-grande-v2-beta | generation |
| babi_qa:task=19,model=ai21_j1-jumbo | generation |
| babi_qa:task=19,model=ai21_j1-large | generation |
| babi_qa:task=19,model=ai21_j2-grande | generation |
| babi_qa:task=19,model=ai21_j2-jumbo | generation |
| babi_qa:task=19,model=ai21_j2-large | generation |
| babi_qa:task=19,model=anthropic_stanford-online-all-v4-s3 | generation |
| babi_qa:task=19,model=cohere_command-medium-beta | generation |
| babi_qa:task=19,model=cohere_command-xlarge-beta | generation |
| babi_qa:task=19,model=cohere_large-20220720 | generation |
| babi_qa:task=19,model=cohere_medium-20220720 | generation |
| babi_qa:task=19,model=cohere_medium-20221108 | generation |
| babi_qa:task=19,model=cohere_small-20220720 | generation |
| babi_qa:task=19,model=cohere_xlarge-20220609 | generation |
| babi_qa:task=19,model=cohere_xlarge-20221108 | generation |
| babi_qa:task=19,model=microsoft_TNLGv2_530B | generation |
| babi_qa:task=19,model=microsoft_TNLGv2_7B | generation |
| babi_qa:task=19,model=openai_ada | generation |
| babi_qa:task=19,model=openai_babbage | generation |
| babi_qa:task=19,model=openai_code-cushman-001 | generation |
| babi_qa:task=19,model=openai_code-davinci-002 | generation |
| babi_qa:task=19,model=openai_curie | generation |
| babi_qa:task=19,model=openai_davinci | generation |
| babi_qa:task=19,model=openai_gpt-3.5-turbo-0301 | generation |
| babi_qa:task=19,model=openai_text-ada-001 | generation |
| babi_qa:task=19,model=openai_text-babbage-001 | generation |
| babi_qa:task=19,model=openai_text-curie-001 | generation |
| babi_qa:task=19,model=openai_text-davinci-002 | generation |
| babi_qa:task=19,model=openai_text-davinci-003 | generation |
| babi_qa:task=19,model=together_bloom | generation |
| babi_qa:task=19,model=together_glm,stop=hash | generation |
| babi_qa:task=19,model=together_gpt-j-6b | generation |
| babi_qa:task=19,model=together_gpt-neox-20b | generation |
| babi_qa:task=19,model=together_opt-175b | generation |
| babi_qa:task=19,model=together_opt-66b | generation |
| babi_qa:task=19,model=together_redpajama-incite-base-3b-v1 | generation |
| babi_qa:task=19,model=together_t0pp,stop=hash | generation |
| babi_qa:task=19,model=together_t5-11b,stop=hash | generation |
| babi_qa:task=19,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| babi_qa:task=19,model=together_yalm | generation |
| babi_qa:task=19,model=writer_palmyra-instruct-30 | generation |
| babi_qa:task=19,model=writer_palmyra-x | generation |
| babi_qa:task=3,model=AlephAlpha_luminous-base | generation |
| babi_qa:task=3,model=AlephAlpha_luminous-extended | generation |
| babi_qa:task=3,model=AlephAlpha_luminous-supreme | generation |
| babi_qa:task=3,model=ai21_j1-grande | generation |
| babi_qa:task=3,model=ai21_j1-grande-v2-beta | generation |
| babi_qa:task=3,model=ai21_j1-jumbo | generation |
| babi_qa:task=3,model=ai21_j1-large | generation |
| babi_qa:task=3,model=ai21_j2-grande | generation |
| babi_qa:task=3,model=ai21_j2-jumbo | generation |
| babi_qa:task=3,model=ai21_j2-large | generation |
| babi_qa:task=3,model=anthropic_stanford-online-all-v4-s3 | generation |
| babi_qa:task=3,model=cohere_command-medium-beta | generation |
| babi_qa:task=3,model=cohere_command-xlarge-beta | generation |
| babi_qa:task=3,model=cohere_large-20220720 | generation |
| babi_qa:task=3,model=cohere_medium-20220720 | generation |
| babi_qa:task=3,model=cohere_medium-20221108 | generation |
| babi_qa:task=3,model=cohere_small-20220720 | generation |
| babi_qa:task=3,model=cohere_xlarge-20220609 | generation |
| babi_qa:task=3,model=cohere_xlarge-20221108 | generation |
| babi_qa:task=3,model=microsoft_TNLGv2_530B | generation |
| babi_qa:task=3,model=microsoft_TNLGv2_7B | generation |
| babi_qa:task=3,model=openai_ada | generation |
| babi_qa:task=3,model=openai_babbage | generation |
| babi_qa:task=3,model=openai_code-cushman-001 | generation |
| babi_qa:task=3,model=openai_code-davinci-002 | generation |
| babi_qa:task=3,model=openai_curie | generation |
| babi_qa:task=3,model=openai_davinci | generation |
| babi_qa:task=3,model=openai_gpt-3.5-turbo-0301 | generation |
| babi_qa:task=3,model=openai_text-ada-001 | generation |
| babi_qa:task=3,model=openai_text-babbage-001 | generation |
| babi_qa:task=3,model=openai_text-curie-001 | generation |
| babi_qa:task=3,model=openai_text-davinci-002 | generation |
| babi_qa:task=3,model=openai_text-davinci-003 | generation |
| babi_qa:task=3,model=together_bloom | generation |
| babi_qa:task=3,model=together_glm,stop=hash | generation |
| babi_qa:task=3,model=together_gpt-j-6b | generation |
| babi_qa:task=3,model=together_gpt-neox-20b | generation |
| babi_qa:task=3,model=together_opt-175b | generation |
| babi_qa:task=3,model=together_opt-66b | generation |
| babi_qa:task=3,model=together_redpajama-incite-base-3b-v1 | generation |
| babi_qa:task=3,model=together_t0pp,stop=hash | generation |
| babi_qa:task=3,model=together_t5-11b,stop=hash | generation |
| babi_qa:task=3,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| babi_qa:task=3,model=together_yalm | generation |
| babi_qa:task=3,model=writer_palmyra-instruct-30 | generation |
| babi_qa:task=3,model=writer_palmyra-x | generation |
| babi_qa:task=all,model=AlephAlpha_luminous-base | generation |
| babi_qa:task=all,model=AlephAlpha_luminous-extended | generation |
| babi_qa:task=all,model=AlephAlpha_luminous-supreme | generation |
| babi_qa:task=all,model=ai21_j1-grande | generation |
| babi_qa:task=all,model=ai21_j1-grande-v2-beta | generation |
| babi_qa:task=all,model=ai21_j1-jumbo | generation |
| babi_qa:task=all,model=ai21_j1-large | generation |
| babi_qa:task=all,model=ai21_j2-grande | generation |
| babi_qa:task=all,model=ai21_j2-jumbo | generation |
| babi_qa:task=all,model=ai21_j2-large | generation |
| babi_qa:task=all,model=anthropic_stanford-online-all-v4-s3 | generation |
| babi_qa:task=all,model=cohere_command-medium-beta | generation |
| babi_qa:task=all,model=cohere_command-xlarge-beta | generation |
| babi_qa:task=all,model=cohere_large-20220720 | generation |
| babi_qa:task=all,model=cohere_medium-20220720 | generation |
| babi_qa:task=all,model=cohere_medium-20221108 | generation |
| babi_qa:task=all,model=cohere_small-20220720 | generation |
| babi_qa:task=all,model=cohere_xlarge-20220609 | generation |
| babi_qa:task=all,model=cohere_xlarge-20221108 | generation |
| babi_qa:task=all,model=microsoft_TNLGv2_530B | generation |
| babi_qa:task=all,model=microsoft_TNLGv2_7B | generation |
| babi_qa:task=all,model=openai_ada | generation |
| babi_qa:task=all,model=openai_babbage | generation |
| babi_qa:task=all,model=openai_code-cushman-001 | generation |
| babi_qa:task=all,model=openai_code-davinci-002 | generation |
| babi_qa:task=all,model=openai_curie | generation |
| babi_qa:task=all,model=openai_davinci | generation |
| babi_qa:task=all,model=openai_gpt-3.5-turbo-0301 | generation |
| babi_qa:task=all,model=openai_text-ada-001 | generation |
| babi_qa:task=all,model=openai_text-babbage-001 | generation |
| babi_qa:task=all,model=openai_text-curie-001 | generation |
| babi_qa:task=all,model=openai_text-davinci-002 | generation |
| babi_qa:task=all,model=openai_text-davinci-003 | generation |
| babi_qa:task=all,model=together_bloom | generation |
| babi_qa:task=all,model=together_glm,stop=hash | generation |
| babi_qa:task=all,model=together_gpt-j-6b | generation |
| babi_qa:task=all,model=together_gpt-neox-20b | generation |
| babi_qa:task=all,model=together_opt-175b | generation |
| babi_qa:task=all,model=together_opt-66b | generation |
| babi_qa:task=all,model=together_redpajama-incite-base-3b-v1 | generation |
| babi_qa:task=all,model=together_t0pp,stop=hash | generation |
| babi_qa:task=all,model=together_t5-11b,stop=hash | generation |
| babi_qa:task=all,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| babi_qa:task=all,model=together_yalm | generation |
| babi_qa:task=all,model=writer_palmyra-instruct-30 | generation |
| babi_qa:task=all,model=writer_palmyra-x | generation |
| bbq:subject=all,method=multiple_choice_joint,model=AlephAlpha_luminous-base | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=AlephAlpha_luminous-extended | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=AlephAlpha_luminous-supreme | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j1-grande | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j1-grande-v2-beta | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j1-jumbo | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j1-large | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j2-grande | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j2-jumbo | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=ai21_j2-large | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3 | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=cohere_command-medium-beta | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=cohere_command-xlarge-beta | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=cohere_large-20220720 | multiple_choice_joint |
| bbq:subject=all,method=multiple_choice_joint,model=cohere_medium-20220720 | multiple_choice_joint |