From 89a633d0028643533d6ac6e86def960eb21c64d1 Mon Sep 17 00:00:00 2001
From: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com>
Date: Tue, 17 Dec 2024 13:15:04 +0100
Subject: [PATCH] Add latest PyTorch DLC with bumped dependencies

---
 .../transformers/4.47.0/py311/Dockerfile      | 101 ++++++++++++++++++
 1 file changed, 101 insertions(+)
 create mode 100644 containers/pytorch/training/gpu/2.3.0/transformers/4.47.0/py311/Dockerfile

diff --git a/containers/pytorch/training/gpu/2.3.0/transformers/4.47.0/py311/Dockerfile b/containers/pytorch/training/gpu/2.3.0/transformers/4.47.0/py311/Dockerfile
new file mode 100644
index 00000000..40c8b734
--- /dev/null
+++ b/containers/pytorch/training/gpu/2.3.0/transformers/4.47.0/py311/Dockerfile
@@ -0,0 +1,101 @@
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+
+LABEL maintainer="Hugging Face"
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Versions
+ARG CUDA="cu121"
+ARG PYTORCH="2.3.0"
+ARG FLASH_ATTN="2.7.2"
+ARG TRANSFORMERS="4.47.0"
+ARG HUGGINGFACE_HUB="0.27.0"
+ARG DIFFUSERS="0.31.0"
+ARG PEFT="0.14.0"
+ARG TRL="0.13.0"
+ARG BITSANDBYTES="0.45.0"
+ARG DATASETS="3.2.0"
+ARG ACCELERATE="1.2.1"
+ARG EVALUATE="0.4.3"
+ARG SENTENCE_TRANSFORMERS="3.3.1"
+ARG DEEPSPEED="0.16.1"
+ARG MAX_JOBS=4
+
+RUN apt-get update && \
+    apt-get install software-properties-common -y && \
+    add-apt-repository ppa:deadsnakes/ppa && \
+    apt-get -y upgrade --only-upgrade systemd openssl cryptsetup && \
+    apt-get install -y \
+    build-essential \
+    bzip2 \
+    curl \
+    git \
+    git-lfs \
+    tar \
+    gcc \
+    g++ \
+    cmake \
+    libprotobuf-dev \
+    libaio-dev \
+    protobuf-compiler \
+    python3.11 \
+    python3.11-dev \
+    libsndfile1-dev \
+    ffmpeg && \
+    && apt-get clean autoremove --yes \
+    && rm -rf /var/lib/{apt,dpkg,cache,log}
+
+# Set Python 3.11 as the default python version
+RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1 && \
+    ln -sf /usr/bin/python3.11 /usr/bin/python
+
+# Install pip from source
+RUN curl -O https://bootstrap.pypa.io/get-pip.py && \
+    python get-pip.py && \
+    rm get-pip.py
+
+# Update pip
+RUN pip install --upgrade pip
+
+# Install latest release PyTorch (PyTorch must be installed before any DeepSpeed c++/cuda ops.)
+RUN pip install --no-cache-dir -U torch==${PYTORCH} torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/${CUDA}
+
+# Upgrade FlashAttnV2
+RUN pip install --no-cache-dir packaging ninja
+RUN MAX_JOBS=${MAX_JOBS} pip install flash-attn==${FLASH_ATTN} --no-build-isolation
+
+# Install Hugging Face Libraries
+RUN pip install --upgrade --no-cache-dir \
+    transformers[sklearn,sentencepiece,vision]==${TRANSFORMERS} \
+    huggingface_hub[hf_transfer]==${HUGGINGFACE_HUB} \
+    diffusers==${DIFFUSERS} \
+    datasets==${DATASETS} \
+    accelerate==${ACCELERATE} \
+    evaluate==${EVALUATE} \
+    peft==${PEFT} \
+    trl==${TRL} \
+    sentence-transformers==${SENTENCE_TRANSFORMERS} \
+    deepspeed==${DEEPSPEED} \
+    bitsandbytes==${BITSANDBYTES} \
+    tensorboard \
+    jupyter notebook
+
+ENV HF_HUB_ENABLE_HF_TRANSFER="1"
+
+# Install Google Cloud Dependencies
+RUN pip install --upgrade --no-cache-dir \
+    google-cloud-storage \
+    google-cloud-bigquery \
+    google-cloud-aiplatform \
+    google-cloud-pubsub \
+    google-cloud-logging \
+    "protobuf<4.0.0"
+
+# Install Google CLI single command
+RUN echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" \
+    | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list && \
+    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg \
+    | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - && \
+    apt-get update -y && \
+    apt-get install google-cloud-sdk -y && \
+    apt-get clean autoremove --yes && \
+    rm -rf /var/lib/{apt,dpkg,cache,log}