Basic Steps to Run an ML Job on NuNet as a Service Provider:

1. Download and install the Device Management Service (DMS): Install the DMS on your machine, which will enable you to request ML jobs by connecting you to compute provider machines that are onboarded on the NuNet platform.

2. Download and install the Service Provider Dashboard (SPD): Install the Service Provider Dashboard on your local machine, making it accessible for you to submit and monitor your ML jobs. No sign-up or NuNet account is needed.

3. Obtain compute resources: Open your preferred browser and visit localhost:9991 to specify the type of compute resources you require (CPU or GPU) and the amount of resources needed for your ML job.

4. Define your ML job: Specify your ML model URL, and provide any additional dependencies required for the execution of the ML job.

5. Set up your wallet: Connect your Cardano wallet (Eternl or Nami wallet) to the Service Provider Dashboard. Ensure that your wallet has enough ADA and NTX tokens for running the ML job and covering transaction fees. For Public Alpha we are using the PreProd Cardano Network.

6. Set a budget: Determine the maximum amount of NTX tokens you are willing to spend on the ML job. This budget will be locked in the smart contract on the PreProd Cardano Network as a guarantee for the compute providers.

7. Submit your ML job: Review your job configuration and submit the ML job to the NuNet platform. The platform will automatically match your job with suitable compute providers based on the resources needed.

8. Monitor your job: Track the progress of your ML job through the Service Provider Dashboard. You can check the log outputs of your job every 2 minutes since your job begins. Please wait for around 5 minutes for the first log to appear when deploying new ML jobs.

9. Review the results: Once the ML job is completed, you can download the output data and review the results. The locked NTX tokens will be released and distributed as a reward to the compute providers who contributed resources to your job.

10. Repeat the process (optional): If you have more ML jobs to run, you can follow the same steps to execute them on the NuNet platform, utilizing its decentralized computing resources.

[Add YouTube video on running the Public Alpha as a Service Provider.]

Basic Steps to Onboard a Machine as a Compute Provider on NuNet:

1. Download and install the Device Management Service (DMS): Install the DMS on your machine, which will enable you to connect to the NuNet platform and make your computing resources available for running ML jobs.

2. Download and install the Compute Provider Dashboard (CPD) : Install the Compute Provider Dashboard on your local machine, making it accessible for you to manage and monitor the ML jobs assigned to your machine and receive NTX tokens for your contributions.

3. Onboard your machine: Please refer to our CPD and NuNet CLI user guides for complete details on how to onboard your machine.

   1. Specify your Cardano address: During the DMS onboarding process, provide the Cardano address of the wallet connected to the Compute Provider Dashboard when using the NuNet CLI. This address will be used for receiving NTX token rewards for your deployment contributions. For Public Alpha we are using the PreProd Cardano Network.

   2. Allocate your Resources: Completing the onboarding process for your machine makes it available for receiving ML job requests while connected to the NuNet platform. Onboarding allows providing the necessary information about your machine to NuNet's Distributed Hash Table, or DHT, such as the available CPU or GPU resources, RAM, and other hardware details. This information will be used to match your machine with ML jobs requiring appropriate resources to deploy them.

4. Create Cardano testnet wallet: Make sure you choose the testnet network when setting up your wallet (Eternl or Nami wallet). The name of the specific Cardano testnet would be PreProd Cardano Network.

5. Set up your wallet: Connect your Cardano wallet to the Compute Provider Dashboard at localhost:9992. Ensure that your wallet has enough tADA for transaction fees. This wallet will be used to receive the NTX tokens on the PreProd Cardano Network as a reward for providing compute resources on NuNet. Make sure the wallet address on this wallet is the same as you specified in Step 3.1 when requesting your NTX tokens.

6. Receive ML jobs: Your machine will be automatically assigned ML jobs based on the resources needed and your machine's availability.

7. Receive NTX token rewards: Upon the successful completion of an ML job, you will receive NTX token rewards in your connected wallet. The amount of NTX tokens received will be based on the resources contributed and the terms set by the service provider.

8. Continue providing compute resources: Keep your machine connected to the NuNet platform and continue providing compute resources for ML jobs, earning NTX tokens as a reward for your contributions.

For a more comprehensive overview, you can always refer to our user guides in the Components Installation section. [Add YouTube video on running the Public Alpha as a Compute Provider.]

Public Alpha is released with the ML use case, which allows users to run simple open source machine learning training on NuNet on-boarded computers and pay for the compute in NTX. We can use widely-used machine learning libraries, such as TensorFlow, PyTorch, and scikit-learn, ensuring that users can effortlessly integrate their preferred tools and frameworks. Moreover, the platform provides the flexibility to run jobs on either CPUs or GPUs, catering to various computational needs and budget constraints.

Designed with a user-centric approach, the Service Provider Dashboard has a simple interface that allows users to easily submit their ML models, define resource usage based on their job requirements, and keep track of their job's progress in real-time. This level of transparency and control empowers users to manage their machine learning jobs effectively and efficiently, ultimately facilitating and accelerating the development & deployment of innovative AI solutions.

For Public Alpha we implemented a smart contract on the PreProd Cardano Network to lock service provider NTX funds and reward compute provider users for the use of their resources.

You need to choose one role to play on this use case: you can be a service provider that will requires to run a ML job on NuNet’s decentralized community hardware or you can be a compute provider who has on-boarded their devices onto the NuNet platform and will be compensated in NTX (NuNet’s Utility Token) for running the ML job requested by some service provider.

During this testing you can contribute in NuNet's development by reporting bugs and suggesting improvements. Please, refer to this documentation about the contribution guidelines: https://gitlab.com/nunet/documentation/-/wikis/Contribution-Guidelines

You can also connect with us on Discord at: https://discord.gg/pg5BnFM89n