1. 15 Jan, 2025 1 commit
    • Baber Abbasi's avatar
      assistant prefill (#2615) · 703fbffd
      Baber Abbasi authored
      * add assistant prefix
      
      * add arc_challenge from llama
      
      * nit
      
      * nit
      
      * nit
      
      * add assistant prefix
      
      * add mmlu_llama
      
      * nit
      
      * nit
      
      * Revert "nit"
      
      This reverts commit 6a97f8356237305e375212b966b30e8de59dd4bc.
      
      * fix regex bug
      
      * add assistant_prefix to vllm
      
      * add `Question:`
      
      * add mmlu_pro
      
      * add fewshot assistant_prefix
      
      * use `assistant_prefill`
      
      * typehints
      
      * nits
      
      * nits
      
      * add to docs
      
      * add readme
      703fbffd
  2. 22 Aug, 2024 1 commit
  3. 05 Aug, 2024 1 commit
    • Yu Shi Jie's avatar
      Mmlu Pro (#1961) · 69d56f45
      Yu Shi Jie authored
      
      
      * initialized mmlu_pro task
      
      * added generative mmlu-pro
      
      * added cot fewshot for mmlu-pro
      
      * Initial commit
      
      * updated mmlu-pro to take on 3 splits: test, val, dev
      
      * mmlu-pro: added continuation and flan_cot_zeroshot
      
      * added README.md for mmlu_pro
      
      * removed
      
      * update files
      
      * moved files out, and removed unused versions
      
      * updated
      
      * mmlu_pro:
      
      -changed task 'other' to 'miscellaneous'
      there is already a group named 'other'
      task and group with the same alias (e.g. mmlu_pro_other_generative) throws an error
      
      -fixed yaml backslash escape for fewshot cot
      
      * changed choices -> options in yaml config to fit dataset schema
      
      * ONLY FOR DEFAULT: fixed yaml file to use variable number of choices
      
      * mmlu-pro: fixed doc_to_text/choice/target configs for all variants
      
      * mmlu-pro: minor fixes
      
      * mmlu-pro/default: aligned with mmlu updates
      
      * mmlu-pro: update yaml content in line with mmlu
      
      * mmlu-pro: fixed mislabelling of task (math->chemistry)
      
      * mmlu-pro: fixed yaml formatting
      
      * add custom fewshot doc_to_text, target, and choice
      
      * add process for each subtask
      
      * add process for each subtask
      
      * pre-commit
      
      * pre-commit
      
      * format
      
      * resolved left out merge
      
      * deleted folders + updated readme
      
      * Update evaluator.py
      
      * Update evaluator.py
      
      ---------
      Co-authored-by: default avatarYu Shi Jie <shijie@tensorplex.ai>
      Co-authored-by: default avatarlintangsutawika <lintang@eleuther.ai>
      Co-authored-by: default avatarroot <root@455bdd73-01.cloud.together.ai>
      Co-authored-by: default avatarLintang Sutawika <lintang@sutawika.com>
      69d56f45