Skip to content

environments acft group relative policy optimization

github-actions[bot] edited this page Dec 30, 2025 · 26 revisions

acft-group-relative-policy-optimization

Overview

Environment used by Group Relative Policy Optimization component

Version: 14

Tags

Preview

View in Studio: https://ml.azure.com/registries/azureml/environments/acft-group-relative-policy-optimization/version/14

Docker image: mcr.microsoft.com/azureml/curated/acft-group-relative-policy-optimization:14

Docker build context

Dockerfile

#PTCA image
FROM mcr.microsoft.com/aifx/acpt/stable-ubuntu2204-cu126-py310-torch280:biweekly.202512.3

USER root

COPY requirements.txt .
RUN pip install -r requirements.txt --no-cache-dir

RUN pip install azureml-evaluate-mlflow==0.0.84
RUN pip install azureml-acft-common-components==0.0.84
RUN pip install transformers==4.56.0

# clean conda and pip caches
RUN rm -rf ~/.cache/pip

# vulnerability in base conda env
RUN conda run -n base python -m pip install --upgrade urllib3>=2.6.0

Clone this wiki locally