.gitattributes

# ─── Text file normalization ───
* text=auto
# ─── Enforce line endings for scripts ─
*.py   text eol=lf
*.sh   text eol=lf
# ─── Treat specific files as binary ─
*.png filter=lfs diff=lfs merge=lfs -text
*.PNG  binary
*.jpg filter=lfs diff=lfs merge=lfs -text
*.JPG  binary
*.jpeg filter=lfs diff=lfs merge=lfs -text
*.gif  binary
*.webp filter=lfs diff=lfs merge=lfs -text
*.pth   binary
*.pt    binary
*.npz   binary
*.npy   binary
# No diff on large JSON data dumps
*.json diff=none
# ─── Merge/Diff Behavior ───
*.lock      merge=ours
*.json      diff=none
*.csv       diff=none
*.tsv       diff=none
# ─── GitHub Linguist Overrides ───
# Don't count Jupyter notebooks as JSON, count them correctly
*.ipynb linguist-language=Jupyter\ Notebook
# Mark documentation folders as documentation, not source
docs/** linguist-documentation
examples/** linguist-documentation
notebooks/** linguist-documentation
# Explicitly classify config/markup languages
*.yml linguist-language=YAML
*.yaml linguist-language=YAML
*.toml linguist-language=TOML
*.ini linguist-language=INI
*.cfg linguist-language=INI
# Ignore data folders from language stats
data/** linguist-vendored
datasets/** linguist-vendored
output/** linguist-generated
checkpoints/** linguist-generated
# Mark scripts and command-line interfaces
scripts/** linguist-language=Python
bin/** linguist-language=Shell
# Custom overrides (optional)
*.md linguist-language=Markdown
*.txt linguist-language=Text
*.bat linguist-language=Batchfile
*.zip filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tar.gz filter=lfs diff=lfs merge=lfs -text
*.tar.bz2 filter=lfs diff=lfs merge=lfs -text
*.tar.xz filter=lfs diff=lfs merge=lfs -text
*.tar.lzma filter=lfs diff=lfs merge=lfs -text
*.tar.lzma filter=lfs diff=lfs merge=lfs -text
*.mkv filter=lfs diff=lfs merge=lfs -text
*.mov filter=lfs diff=lfs merge=lfs -text
*.mp4 filter=lfs diff=lfs merge=lfs -text