[build-system] requires = ["setuptools>=68", "wheel"] build-backend = "setuptools.build_meta" [project] name = "train_u1" version = "0.1.0" description = "Low-VRAM LoRA / partial-finetune trainer for SenseNova-U1-8B-MoT" readme = "README.md" license = { text = "Apache-2.0" } requires-python = ">=3.10" authors = [{ name = "train_u1 contributors" }] keywords = [ "sensenova", "u1", "lora", "diffusion", "flow-matching", "multimodal", "low-vram", ] classifiers = [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "Intended Audience :: Science/Research", "License :: OSI Approved :: Apache Software License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", "Topic :: Scientific/Engineering :: Artificial Intelligence", ] dependencies = [ "torch>=2.9", # Hard-pin: the upstream `modeling_qwen3.py` we vendor (commit df86ca9) # was written against transformers 4.57.1 and reads `config.rope_theta` # directly. transformers 5.x moved that into a `rope_parameters` dict, # which silently breaks attention frequencies and produces noise images # at sample time even when the LoRA + base load cleanly. Stay on 4.57.1 # until we either re-train or rewrite the modeling files. "transformers==4.57.1", "safetensors>=0.7", "huggingface_hub>=0.26", "sentencepiece", "einops", "pillow", "numpy", "bitsandbytes>=0.45", "peft>=0.13", "pyyaml", "pydantic>=2.0", "pyarrow>=14", ] [project.optional-dependencies] dev = ["pytest>=7", "ruff>=0.6"] eval = ["clip-by-openai"] [project.urls] Issues = "https://github.com/OpenSenseNova/SenseNova-U1/issues" Upstream = "https://github.com/OpenSenseNova/SenseNova-U1" ModelCard = "https://huggingface.co/sensenova/SenseNova-U1-8B-MoT" [tool.setuptools.packages.find] include = ["train_u1*"] exclude = ["artifacts*", "dataset*", "hf_cache*", "u1_src*", "tests*"] [tool.setuptools.package-data] train_u1 = ["upstream_pinned_sha256.json"] [tool.pytest.ini_options] testpaths = ["train_u1/tests"] addopts = "-q"