![[ICO]](/icons/blank.gif) | Name | Last modified | Size | Description |
|---|
|
|---|
![[DIR]](/icons/back.gif) | Parent Directory | | - | |
![[DIR]](/icons/folder.gif) | wmt_14:language_pair=ru-en,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=ru-en,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=cs-en,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=hi-en,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=hi-en,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=de-en,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=fr-en,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=de-en,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=cs-en,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| wmt_14:language_pair=fr-en,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 12:10 | - | |
| med_qa:model=meta_llama-3.2-90b-vision-instruct-turbo/ | 18-Oct-2024 11:00 | - | |
| natural_qa:mode=openbook_longans,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| natural_qa:mode=openbook_longans,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| natural_qa:mode=closedbook,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| natural_qa:mode=closedbook,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| narrative_qa:model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| narrative_qa:model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| med_qa:model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=international_citizenship_questions,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=international_citizenship_questions,model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=international_citizenship_questions,model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=proa,model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=international_citizenship_questions,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=proa,model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=proa,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=proa,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=function_of_decision_section,model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=function_of_decision_section,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=function_of_decision_section,model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=function_of_decision_section,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| gsm:model=meta_llama-3.2-11b-vision-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=corporate_lobbying,model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=corporate_lobbying,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=corporate_lobbying,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| gsm:model=meta_llama-3.2-90b-vision-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=corporate_lobbying,model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=abercrombie,model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=abercrombie,model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=abercrombie,model=meta_llama-3.2-11b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| legalbench:subset=abercrombie,model=meta_llama-3.2-90b-vision-instruct-turbo/ | 16-Oct-2024 21:12 | - | |
| wmt_14:language_pair=ru-en,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=ru-en,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=hi-en,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=fr-en,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=hi-en,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=fr-en,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=de-en,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=de-en,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=cs-en,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| wmt_14:language_pair=cs-en,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| natural_qa:mode=closedbook,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| natural_qa:mode=openbook_longans,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| natural_qa:mode=openbook_longans,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| natural_qa:mode=closedbook,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| narrative_qa:model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| narrative_qa:model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| med_qa:model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| med_qa:model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| legalbench:subset=international_citizenship_questions,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| legalbench:subset=international_citizenship_questions,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| gsm:model=qwen_qwen2.5-72b-instruct-turbo,stop=none/ | 16-Oct-2024 19:52 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| gsm:model=qwen_qwen2.5-7b-instruct-turbo,stop=none/ | 16-Oct-2024 19:52 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:52 | - | |
| legalbench:subset=proa,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=proa,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=corporate_lobbying,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=corporate_lobbying,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=function_of_decision_section,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=function_of_decision_section,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=abercrombie,model=qwen_qwen2.5-72b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| legalbench:subset=abercrombie,model=qwen_qwen2.5-7b-instruct-turbo/ | 16-Oct-2024 19:51 | - | |
| eval_cache/ | 15-Oct-2024 17:42 | - | |
| wmt_14:language_pair=de-en,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| wmt_14:language_pair=hi-en,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| wmt_14:language_pair=cs-en,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| wmt_14:language_pair=ru-en,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| wmt_14:language_pair=fr-en,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| med_qa:model=writer_palmyra-x-004/ | 01-Sep-2024 22:21 | - | |
| legalbench:subset=international_citizenship_questions,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| legalbench:subset=corporate_lobbying,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| legalbench:subset=function_of_decision_section,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| legalbench:subset=proa,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:21 | - | |
| natural_qa:mode=openbook_longans,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| natural_qa:mode=closedbook,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| narrative_qa:model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| gsm:model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=writer_palmyra-x-004/ | 01-Sep-2024 22:04 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| legalbench:subset=abercrombie,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 22:04 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004/ | 01-Sep-2024 21:57 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x-004/ | 01-Sep-2024 21:52 | - | |
| med_qa:model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:41 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=writer_palmyra-x-004,stop=none/ | 01-Sep-2024 20:40 | - | |
| narrative_qa:model=writer_palmyra-x-004/ | 29-Aug-2024 09:41 | - | |
|
|---|