Hugging Face's logo

Spaces:
CoreyMorris
/
MMLU-by-task-Leaderboard
Sleeping

App Files Community
4
MMLU-by-task-Leaderboard

Commit History

  1. updated with new data

    CoreyMorris
    e05c716

  2. Updated data and added notes about the site.

    CoreyMorris
    36799a9

  1. update

    CoreyMorris
    28fcccf

  1. Updated with new results 11-21

    CoreyMorris
    3ebf7a7

  1. updated dashboard with new data

    CoreyMorris
    443052d

  1. check for URL and full model name

    Corey Morris
    2037152

  2. updated readme and requirements

    Corey Morris
    9ecc99c

  3. updated sdk version:

    Corey Morris
    f850243

  1. removed streamlit as a requirement

    Corey Morris
    a2fb743

  2. removed version requirements

    Corey Morris
    ac8338a

  3. added new result data

    Corey Morris
    94715ee

  4. Added clickable links (#1)⁠

    Corey
    Unverified signature
    59c6dd2

  1. updated description

    Corey Morris
    cb2c32e

  2. Added new results

    Corey Morris
    f839734

  3. removed example table with link

    Corey Morris
    5d3a9b2

  4. changed default scatter plot index

    Corey Morris
    25bce6d

  5. update

    Corey Morris
    991fb2a

  1. Loading new csv with updated data

    Corey Morris
    a0c39f5

  2. moved organization column to the front

    Corey Morris
    7d69bda

  3. Moved moral scenarios information higher on page

    Corey Morris
    41d7691

  4. changed the wording of moral scenarios

    Corey Morris
    e7c50af

  5. stripping the whitespace from the input so that the filtering works with or without whitespace

    Corey Morris
    e1345be

  6. Support for multi column filtering using comma seperated values (#2)⁠

    CoreyMorris +1: imdatta0
    246a992

  1. Updated

    Corey Morris
    b601bef

  2. Updated description and data

    Corey Morris
    383dc16

  3. updated

    Corey Morris
    65e92dc

  4. Completed loaded form csv

    Corey Morris
    8ef77e5

  5. loading from csv instead of processing data each time

    Corey Morris
    28e8799

  6. updated

    Corey Morris
    667f9a4

  7. WIP. Loading data from csv

    Corey Morris
    1a1910c

  1. Changed error logging from print statements to logger. It is not currently working to save to a file locally

    Corey Morris
    d96fdf9

  2. Catching exceptions in processing files. As new data is introduced, I want to know which files may have different formats and cause problems, but the application shouldn't halt if it can't process a single file

    Corey Morris
    68bce52

  3. Added new results from hugging face evaluations

    Corey Morris
    ad0b971

  1. added code to split moral scenario question from one question to two

    Corey Morris
    65d6581

  2. updated gitignore

    Corey Morris
    76c8220

  3. updated dev requirements

    Corey Morris
    5ca617c

  1. Extracted plotting functions from moral_app to plotting_utils to improve organization and testability

    Corey Morris
    2b55a03

  2. copied main streamlit application to one that will specifically investigate moral reasoning

    Corey Morris
    298ba1f

  1. updated date and model count

    Corey Morris
    0c07f8b

  2. updated results

    Corey Morris
    f1eba6e

  1. Added new hugging face results

    Corey Morris
    3f507e0

  1. added a test and removed the code to only test a specific file because that code did not work

    Corey Morris
    6ed8672

  2. updated to run submodule update

    Corey Morris
    25d217c

  3. Update pytest run to only run specific test files. Other test files are not ready to be run on a different system yet

    Corey Morris
    9345a86

  4. Merge branch 'main' of https://github.com/c1505/LLM-Dashboard into main

    Corey Morris
    0e575e0

  5. Added additional results

    Corey Morris
    7863417

  6. Updated to reflect number of models. Previously, I think there were duplicates

    Corey Morris
    d396c1e

  7. Create python-app.yml

    Corey
    Unverified signature
    063ba51

  8. Updated dependencies

    Corey Morris
    73da8d6

  9. Show a random question from the moral scenarios evaluation

    Corey Morris
    19c7c67