Skip to content
@giganticode

giganticode

Popular repositories Loading

  1. codeprep codeprep Public

    A toolkit for pre-processing large source code corpora

    Python 47 11

  2. run_bug_run run_bug_run Public

    The RunBugRun dataset of executable bugs

    Ruby 23 5

  3. jemma jemma Public

    JEMMA: An Extensible Java dataset for Many ML4Code Applications

    Python 20 7

  4. probes probes Public

    Probing pre-trained source code models

    Python 15 4

  5. langmodels langmodels Public

    Applying machine learning to large source code corpora

    Python 8 2

  6. bohr bohr Public

    Big Old Heuristic Repository

    Python 6 2

Repositories

Showing 10 of 38 repositories
  • throwbench Public

    ThrowBench Code LLM benchmark

    Python 0 0 0 0 Updated Mar 6, 2025
  • bohr-runtime Public
    Python 0 MIT 0 28 10 Updated Feb 28, 2025
  • llm_ingredient_extraction Public
    Python 0 0 0 0 Updated Feb 13, 2025
  • bohr Public

    Big Old Heuristic Repository

    Python 6 MIT 2 19 12 Updated Jan 29, 2025
  • datasets Public
    Shell 0 Apache-2.0 0 0 1 Updated May 3, 2024
  • inspect Public
    Python 1 1 0 0 Updated Nov 26, 2023
  • out_of_context_paper_data Public

    Data and training scripts for the paper "Out of Context: How important is Local Context in Neural Program Repair?"

    Python 1 0 0 0 Updated Nov 20, 2023
  • run_bug_run Public

    The RunBugRun dataset of executable bugs

    Ruby 23 5 2 0 Updated Aug 24, 2023
  • run_bug_run_data Public

    Data Repository for the RunBugRun APR dataset

    1 0 0 0 Updated Apr 11, 2023
  • rbugr Public
    HTML 0 0 0 0 Updated Mar 29, 2023
View all repositories