Files
transformers/docker/custom-tokenizers.dockerfile
Yih-Dar 96d245a83d torch 2.9 don't ❤️ torchcodec 💔 (#41610)
pin

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2025-10-15 14:34:00 +02:00

36 lines
1.9 KiB
Docker

FROM python:3.10-slim
ENV PYTHONDONTWRITEBYTECODE=1
ARG REF=main
USER root
RUN apt-get update && apt-get install -y libsndfile1-dev espeak-ng time git cmake wget xz-utils build-essential g++5 libprotobuf-dev protobuf-compiler git-lfs curl
ENV UV_PYTHON=/usr/local/bin/python
RUN pip --no-cache-dir install uv && uv pip install --no-cache-dir -U pip setuptools
RUN wget https://github.com/ku-nlp/jumanpp/releases/download/v2.0.0-rc3/jumanpp-2.0.0-rc3.tar.xz
RUN tar xvf jumanpp-2.0.0-rc3.tar.xz
RUN mkdir jumanpp-2.0.0-rc3/bld
WORKDIR ./jumanpp-2.0.0-rc3/bld
RUN wget -LO catch.hpp https://github.com/catchorg/Catch2/releases/download/v2.13.8/catch.hpp
RUN mv catch.hpp ../libs/
RUN cmake .. -DCMAKE_INSTALL_PREFIX=/usr/local
RUN make install -j 10
WORKDIR /
RUN uv pip install --no-cache --upgrade 'torch<2.9' --index-url https://download.pytorch.org/whl/cpu
RUN uv pip install --no-cache-dir --no-deps accelerate --extra-index-url https://download.pytorch.org/whl/cpu
RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[ja,testing,sentencepiece,spacy,ftfy,rjieba]" unidic unidic-lite
# spacy is not used so not tested. Causes to failures. TODO fix later
RUN uv run python -m unidic download
# fetch test data and hub objects within CircleCI docker images to reduce even more connections
# we don't need a full clone of `transformers` to run `fetch_hub_objects_for_ci.py`
# the data are downloaded to the directory `/test_data` and during CircleCI's CI runtime, we need to move them to the root of `transformers`
RUN mkdir test_data && cd test_data && curl -O https://raw.githubusercontent.com/huggingface/transformers/${REF}/utils/fetch_hub_objects_for_ci.py && python3 fetch_hub_objects_for_ci.py
RUN uv pip uninstall transformers
RUN apt-get clean && rm -rf /var/lib/apt/lists/*
RUN apt remove -y g++ cmake xz-utils libprotobuf-dev protobuf-compiler