haesleinhuepf/human-eval-bia

Issues

• [Fixing Test Cases] Label Images - When should 0 be considered a label?

  #130 opened 16 days ago by ian-coccimiglio
  2

• grouping test cases and categorisation

  #112 opened 21 days ago by pr4deepr
  23

• New benchmark run from scratch

  #128 opened 17 days ago by haesleinhuepf
  0

• [Fixing Test-Cases] Pandas/Numpy use different stdev estimators (mean_std_column)

  #124 opened 17 days ago by ian-coccimiglio
  2

• [Fixing Test-Cases] Functions with image inputs but checking lists

  #120 opened 17 days ago by ian-coccimiglio
  0

• Guarding against LLMs that would learn our repo "by heart"

  #119 opened 18 days ago by tischi
  1

• Should we represent images using default numpy.asarray()?

  #115 opened 19 days ago by ian-coccimiglio
  2

• Maximum and Sum Intensity Projection Tests

  #116 opened 19 days ago by ian-coccimiglio
  1

• Reference of test case failing with numpy 2.0.2

  #114 opened 20 days ago by haesleinhuepf
  0

• Remove small labels: Unclear prompt

  #111 opened 22 days ago by tischi
  6

• Potential test case: Save voxel size in meta data

  #109 opened 22 days ago by haesleinhuepf
  0

• LLM's using this repo as training data

  #89 opened 2 months ago by JoOkuma
  6

• model names with : cause issues in create_samples.ipynb

  #102 opened 25 days ago by haesleinhuepf
  0

• test cases suggestions

  #99 opened a month ago by pr4deepr
  2

• Test cases from the Icy / Fiji or Java ecosystems?

  #74 opened 3 months ago by tinevez
  6

• What about future models learning from our resource?

  #53 opened 5 months ago by tischi
  5

• Are OME-Zarr tests in scope

  #98 opened a month ago by jluethi
  1

• Curiosity: If test fails, add to prompt the error description?

  #97 opened a month ago by ClementCaporal
  2

• Benchmark gemini-1.5-pro and gemini ultra

  #26 opened a month ago by haesleinhuepf
  0

• Improve how we ask the LLMs to perform a task

  #79 opened 3 months ago by tischi
  12

• Error: name 'Python' is not defined - in llama models

  #80 opened a month ago by ian-coccimiglio
  3

• Check why rather basic test-cases are failing

  #76 opened 3 months ago by haesleinhuepf
  4

• Benchmark llama3.1 405b

  #84 opened 2 months ago by haesleinhuepf
  0

• Add test case: Save image according to ome-ngff standards

  #73 opened 3 months ago by ClementCaporal
  3

• Evaluating LLMs capabilities relative to task-complexity

  #77 opened 3 months ago by ian-coccimiglio
  7

• Report about system prompt in the paper

  #75 opened 3 months ago by haesleinhuepf
  2

• One model often fails with the same error

  #52 opened 3 months ago by haesleinhuepf
  1

• measure execution time of tests

  #71 opened 3 months ago by haesleinhuepf
  0

• count number of comments in generated code

  #70 opened 3 months ago by haesleinhuepf
  0

• add test-case for cell tracking measuring the speed of a cell and/or number of cells over time

  #68 opened 3 months ago by haesleinhuepf
  0

• Add CONTRIBUTING guide and code of conduct

  #44 opened 5 months ago by haesleinhuepf
  1

• rename codellama

  #64 opened 5 months ago by haesleinhuepf
  1

• Timeout when sampling

  #60 opened 5 months ago by haesleinhuepf
  1

• Benchmark against bigger open models

  #59 opened 5 months ago by dcfidalgo
  6

• Samples lost due to error when sampling

  #61 opened 5 months ago by haesleinhuepf
  1

• Mistral benchmarking on blablador currently fails

  #55 opened 5 months ago by haesleinhuepf
  0

• add use case: use aicsimageio to load a file

  #22 opened 5 months ago by haesleinhuepf
  0

• Use pytorch and/or tensorflow?

  #47 opened 5 months ago by haesleinhuepf
  0

• add test case for neuroimaging: load nifti file

  #24 opened 5 months ago by nscherf
  3

• add test for linear intensity profile

  #36 opened 5 months ago by haesleinhuepf
  0

• How to deal with tests that fail due to missing dependencies

  #39 opened 5 months ago by tischi
  6

• add use case: tiled processing

  #23 opened 5 months ago by haesleinhuepf
  0

• add test for circle fitting?

  #35 opened 5 months ago by tischi
  2

• add test for radial intensity profile

  #34 opened 5 months ago by tischi
  1

• Histogram equalization of an image

  #37 opened 5 months ago by haesleinhuepf
  0

• add use case: read zarr file

  #21 opened 5 months ago by haesleinhuepf
  2

• Simple tests involving the file system don't pass

  #12 opened 5 months ago by haesleinhuepf
  2

• UMAP unit-tests don't pass due to timeout

  #14 opened 5 months ago by haesleinhuepf
  1

• How to evaluate

  #17 opened 6 months ago by tischi
  6

• sample canonical solution

  #11 opened 6 months ago by haesleinhuepf
  0