Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
jan-grzybek-ampere authored Feb 1, 2024
1 parent 370073b commit a4f1b0d
Showing 1 changed file with 4 additions and 21 deletions.
25 changes: 4 additions & 21 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,33 +4,16 @@ Model Library goal is to provide facilities necessary for:
- testing accuracy of AI models on data representative of their envisioned task
- aiding comparison of and experiments on various available AI architectures

## Ampere-optimized framework setup

Visit https://solutions.amperecomputing.com/solutions/ampere-ai to obtain the latest available Docker image for your framework of choice.

Go to Downloads section and click on EULA and Docker Image, then after accepting EULA and obtaining your unique download URL:

```bash
apt update && apt install docker.io
apt-get update && apt-get install wget
wget -O ampere_framework.tar.gz “<your_unique_url>
docker load < ampere_framework.tar.gz
```

When the docker load completes you will see the name of the image. Please supply it under AML setup as ampere_framework_image.
## AML setup

You can also check available images on the system by running:
Visit [our dockerhub](https://hub.docker.com/u/amperecomputingai) for our frameworks selection.

```bash
docker image ls -a
```

## AML setup

```bash
apt update && apt install -y docker.io git
git clone --recursive https://github.com/AmpereComputingAI/ampere_model_library.git
cd ampere_model_library
docker run --privileged=true --name ampere_framework -v $PWD/:/aml -it ampere_framework_image
docker run --privileged=true -v $PWD/:/aml -it amperecomputingai/pytorch:latest # we also offer onnxruntime and tensorflow
```

Now you should be inside the docker, to setup AML please run:
Expand Down

0 comments on commit a4f1b0d

Please sign in to comment.