transformers Docker & Self-Hosted Deployment

GitHub

Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference...

168,002 stars Python Python 1 file · ~125,860 tokens #audio#deep-learning#deepseek#gemma#glm#hacktoberfest#llm#machine-learning
1. Pull Image (DOCKERHUB) docker pull microsoft/transformers:latest
2. Docker Run (1-Click Launch) docker run -d --name transformers --restart always microsoft/transformers:latest
3. Podman Run podman run -d --name transformers --restart always microsoft/transformers:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/microsoft/transformers:latest
5. ORAS Pull (OCI Artifact) oras pull microsoft/transformers:latest
docker/transformers-tensorflow-gpu/Dockerfile 
FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04
LABEL maintainer="Hugging Face"
LABEL repository="transformers"

RUN apt update && \
    apt install -y bash \
                   build-essential \
                   git \
                   curl \
                   ca-certificates \
                   python3 \
                   python3-pip && \
    rm -rf /var/lib/apt/lists

RUN python3 -m pip install --no-cache-dir --upgrade pip && \
    python3 -m pip install --no-cache-dir \
    mkl \
    tensorflow

WORKDIR /workspace
COPY . transformers/
RUN cd transformers/ && \
    python3 -m pip install --no-cache-dir .

CMD ["/bin/bash"]