[build-system] requires = ["setuptools>=61.0"] build-backend = "setuptools.build_meta" [project] name = "vila" version = "1.0.0" description = "VILA: On Pre-training for Visual Language Models" readme = "README.md" requires-python = ">=3.8" classifiers = [ "Programming Language :: Python :: 3", "License :: OSI Approved :: Apache Software License", ] dependencies = [ "torch==2.3.0", "torchvision==0.18.0", "transformers==4.37.2", "tokenizers>=0.15.2", "sentencepiece==0.1.99", "shortuuid", "accelerate==0.27.2", "peft>=0.9.0", "bitsandbytes==0.41.0", "pydantic<2,>=1", "markdown2[all]", "numpy==1.26.0", "scikit-learn==1.2.2", "gradio==3.35.2", "gradio_client==0.2.9", "requests", "httpx==0.24.0", "uvicorn", "fastapi", "einops==0.6.1", "einops-exts==0.0.4", "timm==0.9.12", "openpyxl==3.1.2", "pytorchvideo==0.1.5", "decord==0.6.0", "datasets==2.16.1", "openai==1.8.0", "webdataset==0.2.86", "nltk==3.3", "pywsd==1.2.4", "opencv-python==4.8.0.74", "s2wrapper@git+https://github.com/bfshi/scaling_on_scales", "tyro", "pytest", "pre-commit" ] [project.scripts] vilarun = "llava.cli.run:main" [project.optional-dependencies] train = ["deepspeed==0.9.5", "ninja", "wandb"] eval = ["word2number", "Levenshtein", "nltk", "pywsd"] [project.urls] "Homepage" = "https://hanlab.mit.edu/projects/vila" "Bug Tracker" = "https://github.com/Efficient-Large-Model/VILA-Internal/issues" [tool.black] line-length = 120 [tool.isort] profile = "black" multi_line_output = 3 include_trailing_comma = true force_grid_wrap = 0 use_parentheses = true ensure_newline_before_comments = true line_length = 120 [tool.setuptools.packages.find] exclude = ["assets*", "benchmark*", "docs", "dist*", "playground*", "scripts*", "tests*"] [tool.wheel] exclude = ["assets*", "benchmark*", "docs", "dist*", "playground*", "scripts*", "tests*"]